The data consists of vegetation % cover by functional group from across CONUS (from AIM, FIA, LANDFIRE, and RAP), as well as climate variables from DayMet, which have been aggregated into mean interannual conditions accross multiple temporal windows.

Dependencies

Set user defined parameters

print(params)
## $run
## [1] FALSE
## 
## $save_figs
## [1] FALSE
## 
## $ecoregion
## [1] "CONUS"
## 
## $response
## [1] "FIA"
## 
## $removeTexasLouisianaPlain
## [1] FALSE
## 
## $trimAnomalies
## [1] TRUE
## 
## $autoKfold
## [1] FALSE
# set to true if want to run for a limited number of rows (i.e. for code testing)
test_run <- params$test_run
save_figs <- params$save_figs
response <- params$response
fit_sample <- TRUE # fit model to a sample of the data
n_train <- 5e4 # sample size of the training data
n_test <- 1e6 # sample size of the testing data (if this is too big the decile dotplot code throws memory errors)
trimAnom <- params$trimAnomalies
removeTLP <- params$removeTexasLouisianaPlain
run <- params$run
autoKfold <- params$autoKfold

Load packages

# set option so resampled dataset created here reproduces earlier runs of this code with dplyr 1.0.10
source("../../../Functions/glmTransformsIterates.R")
source("../../../Functions/transformPreds.R")
source("../../../Functions/StepBeta_mine.R")
#source("src/fig_params.R")
#source("src/modeling_functions.R")
 
library(ggspatial)
library(terra)
library(tidyterra)
library(sf)
library(caret)
library(tidyverse)
library(GGally) # for ggpairs()
library(pdp) # for partial dependence plots
library(gridExtra)
library(knitr)
library(patchwork) # for figure insets etc. 
library(ggtext)
library(StepBeta)
theme_set(theme_classic())
library(here)
library(rsample)
library(kableExtra)
library(glmnet)
library(USA.state.boundaries)

Read in data

Data compiled in the prepDataForModels.R script

here::i_am("Analysis/VegComposition/ModelFitting/02_ModelFitting.Rmd")
modDat <- readRDS("/Users/astears/Documents/Dropbox_static/Work/NAU_USGS_postdoc/PED_vegClimModels/Data_processed/BiomassQuantityData/dataForAnalysis_fireAndDevelopmentRemoved.rds")

modDat_1 <- modDat %>% 
  st_drop_geometry()
# remove second 'x' and 'y' columns
#modDat <- modDat[,c(1:41,43:48)]
# For all response variables, make sure there are no 0s add  .0001 from each, since the Gamma model framework can't handle that
modDat_1[modDat_1$biomass_MgPerHect == 0 & !is.na(modDat_1$biomass_MgPerHect), "biomass_MgPerHect"] <- 0.0001

Prep data

Add a constant to the response variable (+2) so that models run…

modDat_1 <- modDat_1 %>%
mutate(response_transformed = .[["biomass_MgPerHect"]] + 2)

Identify the ecoregion and response variable type to use in this model run

ecoregion <- params$ecoregion
response <- params$response
print(paste0("In this model run, the ecoregion is ", ecoregion," and the data is from ",response))
## [1] "In this model run, the ecoregion is CONUS and the data is from FIA"

Visualize the predictor variables

The following are the candidate predictor variables for this ecoregion:

if (ecoregion == "shrubGrass") {
  # select potential predictor variables for the ecoregion of interest
        prednames <-
          c("tmean", "prcpTempCorr", "isothermality", "annWatDef",
         "prcp", "prcp_seasonality", "prcp_dry", "annWetDegDays",
         "t_warm", "t_cold", "prcp_wet", "soilDepth", "sand", "coarse",
         "AWHC", "clay", "carbon"
# "tmean"             , "prcp"                    ,"prcp_seasonality"        ,"prcpTempCorr"          , 
# "isothermality"     , "annWatDef"               ,"sand"                    ,"coarse"                , 
# "carbon"            , "AWHC"                    ,"tmin_anom"               ,"tmax_anom"             , 
# "t_warm_anom"       , "prcp_wet_anom"           ,"precp_dry_anom"          ,"prcp_seasonality_anom" , 
# "prcpTempCorr_anom" , "aboveFreezingMonth_anom" ,"isothermality_anom"      ,"annWatDef_anom"        , 
# "annWetDegDays_anom", "VPD_mean_anom"           ,"VPD_min_anom"            ,"frostFreeDays_5_anom"  
)
  
} else if (ecoregion %in% c("forest", "eastForest", "westForest")) {
  # select potential predictor variables for the ecoregion of interest
  prednames <- 
    c("tmean", "prcpTempCorr", "isothermality", "annWatDef",
         "prcp", "prcp_seasonality", "prcp_dry", "annWetDegDays",
         "t_warm", "t_cold", "prcp_wet", "soilDepth", "sand", "coarse",
         "AWHC", "clay", "carbon"
# "tmean"                 ,"prcp"               , "prcp_dry"                , "prcpTempCorr"      ,     
# "isothermality"         ,"annWatDef"          , "clay"                    , "sand"              ,     
# "coarse"                ,"carbon"             , "AWHC"                    , "tmin_anom"         ,     
# "tmax_anom"             ,"prcp_anom"          , "prcp_wet_anom"           , "precp_dry_anom"    ,     
# "prcp_seasonality_anom" ,"prcpTempCorr_anom"  , "aboveFreezingMonth_anom" , "isothermality_anom",     
# "annWatDef_anom"        ,"annWetDegDays_anom" , "VPD_mean_anom"           , "VPD_max_95_anom"   ,     
# "frostFreeDays_5_anom"   
)
} else if (ecoregion == "CONUS") {
  prednames <- c("tmean", "prcpTempCorr", "isothermality", "annWatDef",
         "prcp", "prcp_seasonality", "prcp_dry", "annWetDegDays",
         "t_warm", "t_cold", "prcp_wet", "soilDepth", "sand", "coarse",
         "AWHC", "clay", "carbon"
#     "tmean"               ,"prcp"               ,"prcp_seasonality", "prcpTempCorr"       ,  "isothermality"     ,     
# "annWetDegDays"           ,"sand"               ,"coarse"         , "AWHC"                , "tmin_anom"          ,    
# "tmax_anom"               ,"prcp_wet_anom"      ,"precp_dry_anom" , "prcp_seasonality_anom", "prcpTempCorr_anom" ,     
# "aboveFreezingMonth_anom" ,"isothermality_anom" ,"annWatDef_anom" , "annWetDegDays_anom"  , "VPD_mean_anom"      ,    
# "VPD_max_95_anom"         ,"frostFreeDays_5_anom"   
  )
} 

# get the name of the transformed response
#response <- paste0(response, "_transformed")

Scale the predictor variables for the model-fitting process

allPreds <- modDat_1 %>% 
  dplyr::select(tmin:frostFreeDays,#tmean_anom:frostFreeDays_anom, 
                soilDepth:AWHC) %>% 
  names()
modDat_1_s <- modDat_1 %>% 
  mutate(across(all_of(allPreds), base::scale, .names = "{.col}_s")) 
# names(modDat_1_s) <- c(names(modDat_1),
#                        paste0(prednames, "_s")
#                        )
#save model input data after its been scaled
saveRDS(modDat_1_s, file = "./models/scaledModelInputData.rds")

Isolate the data just for the response variable of interest

modDat_1 <- modDat_1 %>% 
  filter(biomassSource == response)
modDat_1_s <- modDat_1_s %>% 
  filter(biomassSource == response)

Subset the data to only include data for the ecoregion of interest

if (ecoregion == "shrubGrass") {
  # select data for the ecoregion of interest
  modDat_1_s <- modDat_1_s %>%
    filter(newRegion == "dryShrubGrass")
} else if (ecoregion == "forest") {
  # select data for the ecoregion of interest
  modDat_1_s <- modDat_1_s %>% 
    filter(newRegion %in% c("eastForest", "westForest"))
} else if (ecoregion == "CONUS") {
  modDat_1_s <- modDat_1_s
} else if (ecoregion == "eastForest") {
   modDat_1_s <- modDat_1_s %>% 
    filter(newRegion == "eastForest")
} else if (ecoregion == "westForest") {
    modDat_1_s <- modDat_1_s %>% 
    filter(newRegion == "westForest")
}
# remove the rows that have no observations for the response variable of interest
modDat_1_s <- modDat_1_s[!is.na(modDat_1_s$biomass_MgPerHect),]
# subset the data to only include these predictors, and remove any remaining NAs 
modDat_1_s <- modDat_1_s %>% 
  dplyr::select(prednames, paste0(prednames, "_s"), biomass_MgPerHect, response_transformed, 
                newRegion, #Year, Long, Lat,
                NA_L1NAME, NA_L2NAME,
                Long, Lat) %>% 
  drop_na()

names(prednames) <- prednames
df_pred <- modDat_1_s[, prednames]
# 
# # print the list of predictor variables
# knitr::kable(format = "html", data.frame("Possible_Predictors" = prednames), row.names = FALSE
# ) %>%
#   kable_styling(bootstrap_options = c("striped", "hover", "condensed"))

Visualize the response variable

hist(modDat_1_s$biomass_MgPerHect, main = paste0("Histogram of ","biomass_MgPerHect"),
     xlab = paste0("biomass_MgPerHect"))

create_summary <- function(df) {
  df %>% 
    pivot_longer(cols = everything(),
                 names_to = 'variable') %>% 
    group_by(variable) %>% 
    summarise(across(value, .fns = list(mean = ~mean(.x, na.rm = TRUE), min = ~min(.x, na.rm = TRUE), 
                                        median = ~median(.x, na.rm = TRUE), max = ~max(.x, na.rm = TRUE)))) %>% 
    mutate(across(where(is.numeric), round, 4))
}

modDat_1_s[prednames] %>% 
  create_summary() %>% 
  knitr::kable(caption = 'summaries of possible predictor variables') %>%
kable_styling(bootstrap_options = c("striped", "hover", "condensed")) 
summaries of possible predictor variables
variable value_mean value_min value_median value_max
AWHC 17.3867 0.1200 17.3224 36.8252
annWatDef 64.6760 0.0000 32.8862 542.9704
annWetDegDays 2913.9390 92.3800 2767.0380 7280.6791
carbon 3.4820 0.0000 1.3175 56.4588
clay 18.6761 0.0198 17.8585 82.7982
coarse 7.9801 0.0000 3.7012 82.9684
isothermality 35.4455 18.8852 35.5695 61.9699
prcp 828.6650 49.7543 786.0965 5329.8773
prcpTempCorr 0.0931 -0.8471 0.1618 0.7152
prcp_dry 13.4314 0.0000 6.6460 81.4120
prcp_seasonality 0.7980 0.3506 0.7757 2.2945
prcp_wet 168.7358 23.1053 166.3858 1082.3220
sand 42.7667 0.0098 41.5580 99.9892
soilDepth 151.8274 3.0000 159.6535 201.0000
t_cold -7.2584 -23.3250 -7.6922 15.3832
t_warm 31.0077 4.6400 31.2279 47.1433
tmean 11.6669 -7.4826 10.9827 24.8830
# response_summary <- modDat_1_s %>% 
#     dplyr::select(#where(is.numeric), -all_of(pred_vars),
#       matches(response)) %>% 
#     create_summary()
# 
# 
# kable(response_summary, 
#       caption = 'summaries of response variables, calculated using paint') %>%
# kable_styling(bootstrap_options = c("striped", "hover", "condensed")) 

Histograms of raw and scaled predictors

scaleFigDat_1 <- modDat_1_s %>% 
  dplyr::select(c(#Long, Lat, Year, 
    Long, Lat, prednames)) %>% 
  pivot_longer(cols = all_of(names(prednames)), 
               names_to = "predNames", 
               values_to = "predValues_unScaled")
scaleFigDat_2 <- modDat_1_s %>% 
  dplyr::select(c(#Long, Lat, Year, 
    Long, Lat, paste0(prednames, "_s"))) %>% 
  pivot_longer(cols = all_of(paste0(prednames,"_s"
                                    )), 
               names_to = "predNames", 
               values_to = "predValues_scaled", 
               names_sep = ) %>% 
  mutate(predNames = str_replace(predNames, pattern = "_s$", replacement = ""))

scaleFigDat_3 <- scaleFigDat_1 %>% 
  left_join(scaleFigDat_2)

ggplot(scaleFigDat_3) + 
  facet_wrap(~predNames, scales = "free") +
  geom_histogram(aes(predValues_unScaled), fill = "lightgrey", col = "darkgrey") + 
  geom_histogram(aes(predValues_scaled), fill = "lightblue", col = "blue") +
  xlab ("predictor variable values") + 
  ggtitle("Comparing the distribution of unscaled (grey) to scaled (blue) predictor variables")

modDat_1_s <- modDat_1_s %>% 
  rename_with(~paste0(.x, "_raw"), 
                any_of(names(prednames))) %>% 
  rename_with(~str_remove(.x, "_s$"), 
              any_of(paste0(names(prednames), "_s")))

Predictor variables compared to binned response variables

set.seed(12011993)
quants <- quantile(modDat_1_s$biomass_MgPerHect)
# vector of name of response variables
vars_response <- "biomass_MgPerHect"
# longformat dataframes for making boxplots
df_sample_plots <-  modDat_1_s  %>% 
  slice_sample(n = 5e4) %>% 
   #rename("biomass_MgPerHect" = all_of(biomass_MgPerHect)) %>% 
  mutate("biomass_MgPerHect" = case_when(
    "biomass_MgPerHect" <= quants[2] ~ paste(round(quants[2],2)), 
    "biomass_MgPerHect" > quants[2] & biomass_MgPerHect <=quants[3] ~ paste(round(quants[3],2)), 
    "biomass_MgPerHect" > quants[3] & biomass_MgPerHect <=quants[4] ~ paste(round(quants[4],2)), 
    "biomass_MgPerHect" >= quants[4]  ~ paste(round(quants[5],2)), 
  )) %>% 
  dplyr::select(c("biomass_MgPerHect", prednames)) %>% 
  tidyr::pivot_longer(cols = unname(prednames), 
               names_to = "predictor", 
               values_to = "value"
               )  
 

  ggplot(df_sample_plots, aes_string(x= "biomass_MgPerHect", y = 'value')) +
  geom_boxplot() +
  facet_wrap(~predictor , scales = 'free_y') + 
  ylab("Predictor Variable Values") + 
    xlab("biomass_MgPerHect")

Model Fitting

Visualize the spatial blocks and how they differ across environmental space

First, if there are observations in Louisiana, sub-sample them so they’re not so over-represented in the dataset

## make data into spatial format
modDat_1_sf <- modDat_1_s %>% 
  st_as_sf(coords = c("Long", "Lat"), crs = st_crs("PROJCRS[\"unnamed\",\n    BASEGEOGCRS[\"unknown\",\n        DATUM[\"unknown\",\n            ELLIPSOID[\"Spheroid\",6378137,298.257223563,\n                LENGTHUNIT[\"metre\",1,\n                    ID[\"EPSG\",9001]]]],\n        PRIMEM[\"Greenwich\",0,\n            ANGLEUNIT[\"degree\",0.0174532925199433,\n                ID[\"EPSG\",9122]]]],\n    CONVERSION[\"Lambert Conic Conformal (2SP)\",\n        METHOD[\"Lambert Conic Conformal (2SP)\",\n            ID[\"EPSG\",9802]],\n        PARAMETER[\"Latitude of false origin\",42.5,\n            ANGLEUNIT[\"degree\",0.0174532925199433],\n            ID[\"EPSG\",8821]],\n        PARAMETER[\"Longitude of false origin\",-100,\n            ANGLEUNIT[\"degree\",0.0174532925199433],\n            ID[\"EPSG\",8822]],\n        PARAMETER[\"Latitude of 1st standard parallel\",25,\n            ANGLEUNIT[\"degree\",0.0174532925199433],\n            ID[\"EPSG\",8823]],\n        PARAMETER[\"Latitude of 2nd standard parallel\",60,\n            ANGLEUNIT[\"degree\",0.0174532925199433],\n            ID[\"EPSG\",8824]],\n        PARAMETER[\"Easting at false origin\",0,\n            LENGTHUNIT[\"metre\",1],\n            ID[\"EPSG\",8826]],\n        PARAMETER[\"Northing at false origin\",0,\n            LENGTHUNIT[\"metre\",1],\n            ID[\"EPSG\",8827]]],\n    CS[Cartesian,2],\n        AXIS[\"easting\",east,\n            ORDER[1],\n            LENGTHUNIT[\"metre\",1,\n                ID[\"EPSG\",9001]]],\n        AXIS[\"northing\",north,\n            ORDER[2],\n            LENGTHUNIT[\"metre\",1,\n                ID[\"EPSG\",9001]]]]"))


# download map info for visualization
data(state_boundaries_wgs84) 

cropped_states <- suppressMessages(state_boundaries_wgs84 %>%
  dplyr::filter(NAME!="Hawaii") %>%
  dplyr::filter(NAME!="Alaska") %>%
  dplyr::filter(NAME!="Puerto Rico") %>%
  dplyr::filter(NAME!="American Samoa") %>%
  dplyr::filter(NAME!="Guam") %>%
  dplyr::filter(NAME!="Commonwealth of the Northern Mariana Islands") %>%
  dplyr::filter(NAME!="United States Virgin Islands") %>%
  sf::st_sf() %>%
  sf::st_transform(sf::st_crs(modDat_1_sf))) #%>%
  #sf::st_crop(sf::st_bbox(modDat_1_sf)+c(-1,-1,1,1))
if (ecoregion %in% c("Forest", "eastForest", "forest")){
modDat_1_s$uniqueID <- 1:nrow(modDat_1_s)
modDat_1_sf$uniqueID <- 1:nrow(modDat_1_sf)

  #xlim(c(730439.1, 1042196))
}
## do a pca of climate across level 2 ecoregions
pca <- prcomp(modDat_1_s[,paste0(prednames)])
library(factoextra)
(fviz_pca_ind(pca, habillage = modDat_1_s$NA_L2NAME, label = "none", addEllipses = TRUE, ellipse.level = .95, ggtheme = theme_minimal(), alpha.ind = .1))

if (ecoregion == "shrubGrass") {
  print("We'll combine the 'Mediterranean California' and 'Western Sierra Madre Piedmont' ecoregions (into 'Mediterranean Piedmont'). We'll also combine `Tamaulipas-Texas semiarid plain,' 'Texas-Lousiana Coastal plain,' and 'South Central semiarid prairies' ecoregions (into (`Semiarid plain and prairies`)." )
  
  modDat_1_s[modDat_1_s$NA_L2NAME %in% c("MEDITERRANEAN CALIFORNIA", "WESTERN SIERRA MADRE PIEDMONT"), "NA_L2NAME"] <- "MEDITERRANEAN PIEDMONT"
  
  modDat_1_s[modDat_1_s$NA_L2NAME %in% c("TAMAULIPAS-TEXAS SEMIARID PLAIN", "TEXAS-LOUISIANA COASTAL PLAIN", "SOUTH CENTRAL SEMIARID PRAIRIES"), "NA_L2NAME"] <- "SEMIARID PLAIN AND PRAIRIES"
 
    modDat_1_s[modDat_1_s$NA_L2NAME %in% c("MARINE WEST COAST FOREST", "WESTERN CORDILLERA"), "NA_L2NAME"] <- "WESTERN CORDILLERA AND WEST COAST FOREST"
  
  modDat_1_s[modDat_1_s$NA_L2NAME %in% c("MEDITERRANEAN CALIFORNIA", "UPPER GILA MOUNTAINS"), "NA_L2NAME"] <- "MEDITERRANEAN CALIFORNIA AND UPPER GILA MOUNTAINS"

modDat_1_s[modDat_1_s$NA_L2NAME %in% c("MIXED WOOD PLAINS", "OZARK/OUACHITA-APPALACHIAN FORESTS"), "NA_L2NAME"] <- "OZARK/OUACHITA-APPALACHIAN FORESTS AND MIXED WOOD PLAINS"
#////
modDat_1_sf[modDat_1_sf$NA_L2NAME %in% c("MEDITERRANEAN CALIFORNIA", "WESTERN SIERRA MADRE PIEDMONT"), "NA_L2NAME"] <- "MEDITERRANEAN PIEDMONT"
  
  modDat_1_sf[modDat_1_sf$NA_L2NAME %in% c("TAMAULIPAS-TEXAS SEMIARID PLAIN", "TEXAS-LOUISIANA COASTAL PLAIN", "SOUTH CENTRAL SEMIARID PRAIRIES"), "NA_L2NAME"] <- "SEMIARID PLAIN AND PRAIRIES"
 
    modDat_1_sf[modDat_1_sf$NA_L2NAME %in% c("MARINE WEST COAST FOREST", "WESTERN CORDILLERA"), "NA_L2NAME"] <- "WESTERN CORDILLERA AND WEST COAST FOREST"
  
  modDat_1_sf[modDat_1_sf$NA_L2NAME %in% c("MEDITERRANEAN CALIFORNIA", "UPPER GILA MOUNTAINS"), "NA_L2NAME"] <- "MEDITERRANEAN CALIFORNIA AND UPPER GILA MOUNTAINS"

modDat_1_sf[modDat_1_sf$NA_L2NAME %in% c("MIXED WOOD PLAINS", "OZARK/OUACHITA-APPALACHIAN FORESTS"), "NA_L2NAME"] <- "OZARK/OUACHITA-APPALACHIAN FORESTS AND MIXED WOOD PLAINS"
 if (response == "CAMCover") {
   modDat_1_s[modDat_1_s$NA_L2NAME %in% c("MEDITERRANEAN PIEDMONT", "SEMIARID PLAIN AND PRAIRIES"), "NA_L2NAME"] <- "SEMIARID PLAIN AND PRAIRIES AND PIEDMONT"
   modDat_1_sf[modDat_1_sf$NA_L2NAME %in% c("MEDITERRANEAN PIEDMONT", "SEMIARID PLAIN AND PRAIRIES"), "NA_L2NAME"] <- "SEMIARID PLAIN AND PRAIRIES AND PIEDMONT"
 } else if (response %in% c("C4GramCover_prop", "C3GramCover_prop")) {
     modDat_1_s[modDat_1_s$NA_L2NAME %in% c("SEMIARID PLAIN AND PRAIRIES", "TEMPERATE PRAIRIES"), "NA_L2NAME"] <- "SEMIARID AND TEMPERATE PRAIRIES"
   modDat_1_sf[modDat_1_sf$NA_L2NAME %in% c("SEMIARID PLAIN AND PRAIRIES", "TEMPERATE PRAIRIES"), "NA_L2NAME"] <- "SEMIARID AND TEMPERATE PRAIRIES" 
 }

} else if (ecoregion == "CONUS") {
  
  modDat_1_s[modDat_1_s$NA_L2NAME %in% c("EVERGLADES", "MISSISSIPPI ALLUVIAL AND SOUTHEAST USA COASTAL PLAINS"), "NA_L2NAME"] <- "EVERGLADES MISSISSIPPI ALLUVIAL AND SOUTHEAST USA COASTAL PLAINS"
  
  modDat_1_s[modDat_1_s$NA_L2NAME %in% c("MARINE WEST COAST FOREST", "WESTERN CORDILLERA"), "NA_L2NAME"] <- "WESTERN CORDILLERA AND WEST COAST FOREST"
  
   modDat_1_s[modDat_1_s$NA_L2NAME %in% c("MIXED WOOD PLAINS", "OZARK/OUACHITA-APPALACHIAN FORESTS"), "NA_L2NAME"] <- "OZARK/OUACHITA-APPALACHIAN FORESTS AND MIXED WOOD PLAINS"
  
   modDat_1_s[modDat_1_s$NA_L2NAME %in% c("MEDITERRANEAN CALIFORNIA", "UPPER GILA MOUNTAINS"), "NA_L2NAME"] <- "MEDITERRANEAN CALIFORNIA AND UPPER GILA MOUNTAINS"
  
   modDat_1_s[modDat_1_s$NA_L2NAME %in% c("OZARK/OUACHITA-APPALACHIAN FORESTS AND MIXED WOOD PLAINS", "SOUTHEASTERN USA PLAINS",  "MISSISSIPPI ALLUVIAL AND SOUTHEAST USA COASTAL PLAINS", "EVERGLADES MISSISSIPPI ALLUVIAL AND SOUTHEAST USA COASTAL PLAINS"), "NA_L2NAME"] <- "SOUTHEASTERN AND MIXED WOOD PLAINS"
   
  modDat_1_s[modDat_1_s$NA_L2NAME %in% c("SOUTH CENTRAL SEMIARID PRAIRIES", "TEXAS-LOUISIANA COASTAL PLAIN"), "NA_L2NAME"] <- "SOUTH CENTRAL SEMIARID PRAIRIES"
  #///
  
  modDat_1_sf[modDat_1_sf$NA_L2NAME %in% c("EVERGLADES", "MISSISSIPPI ALLUVIAL AND SOUTHEAST USA COASTAL PLAINS"), "NA_L2NAME"] <- "EVERGLADES MISSISSIPPI ALLUVIAL AND SOUTHEAST USA COASTAL PLAINS"
  
  modDat_1_sf[modDat_1_sf$NA_L2NAME %in% c("MARINE WEST COAST FOREST", "WESTERN CORDILLERA"), "NA_L2NAME"] <- "WESTERN CORDILLERA AND WEST COAST FOREST"
  
   modDat_1_sf[modDat_1_sf$NA_L2NAME %in% c("MIXED WOOD PLAINS", "OZARK/OUACHITA-APPALACHIAN FORESTS"), "NA_L2NAME"] <- "OZARK/OUACHITA-APPALACHIAN FORESTS AND MIXED WOOD PLAINS"
  
   modDat_1_sf[modDat_1_sf$NA_L2NAME %in% c("MEDITERRANEAN CALIFORNIA", "UPPER GILA MOUNTAINS"), "NA_L2NAME"] <- "MEDITERRANEAN CALIFORNIA AND UPPER GILA MOUNTAINS"
  
   modDat_1_sf[modDat_1_sf$NA_L2NAME %in% c("OZARK/OUACHITA-APPALACHIAN FORESTS AND MIXED WOOD PLAINS", "SOUTHEASTERN USA PLAINS",  "MISSISSIPPI ALLUVIAL AND SOUTHEAST USA COASTAL PLAINS", "EVERGLADES MISSISSIPPI ALLUVIAL AND SOUTHEAST USA COASTAL PLAINS"), "NA_L2NAME"] <- "SOUTHEASTERN AND MIXED WOOD PLAINS"
   
  modDat_1_sf[modDat_1_sf$NA_L2NAME %in% c("SOUTH CENTRAL SEMIARID PRAIRIES", "TEXAS-LOUISIANA COASTAL PLAIN"), "NA_L2NAME"] <- "SOUTH CENTRAL SEMIARID PRAIRIES"
  
  if (response %in% c("C4GramCover_prop")) {
    modDat_1_s[modDat_1_s$NA_L2NAME %in% c("CENTRAL USA PLAINS", "TEMPERATE PRAIRIES", "SOUTHEASTERN AND MIXED WOOD PLAINS", "ATLANTIC HIGHLANDS", "MIXED WOOD SHIELD"), "NA_L2NAME"] <- "EASTERN AND MIXED WOOD PLAINS AND FOREST"
  #///
  
  modDat_1_sf[modDat_1_sf$NA_L2NAME %in%c("CENTRAL USA PLAINS", "TEMPERATE PRAIRIES", "SOUTHEASTERN AND MIXED WOOD PLAINS", "ATLANTIC HIGHLANDS", "MIXED WOOD SHIELD"), "NA_L2NAME"] <- "EASTERN AND MIXED WOOD PLAINS AND FOREST"
  }
} else if (ecoregion == "forest"  & response != "CAMCover") {
   modDat_1_s[modDat_1_s$NA_L2NAME %in% c("MISSISSIPPI ALLUVIAL AND SOUTHEAST USA COASTAL PLAINS", "EVERGLADES"), "NA_L2NAME"] <- "MISSISSIPPI ALLUVIAL AND SOUTHEAST USA COASTAL PLAINS    AND EVERGLADES"
   
   modDat_1_s[modDat_1_s$NA_L2NAME %in% c("UPPER GILA MOUNTAINS", "WESTERN CORDILLERA"), "NA_L2NAME"] <- "WESTERN CORDILLERA AND UPPER GILA MOUNTAINS"
   
   modDat_1_s[modDat_1_s$NA_L2NAME %in% c("MISSISSIPPI ALLUVIAL AND SOUTHEAST USA COASTAL PLAINS\tAND EVERGLADES", "SOUTHEASTERN USA PLAINS"), "NA_L2NAME"] <- "SOUTHEASTERN USA PLAINS"
   
   modDat_1_s[modDat_1_s$NA_L2NAME %in% c("ATLANTIC HIGHLANDS", "OZARK/OUACHITA-APPALACHIAN FORESTS"), "NA_L2NAME"] <- "HIGHLANDS AND APPALACHIAN FORESTS"
   
   modDat_1_s[modDat_1_s$NA_L2NAME %in% c("CENTRAL USA PLAINS", "MIXED WOOD PLAINS"), "NA_L2NAME"] <- "CENTRAL AND MIXED WOOD PLAINS"
   
   modDat_1_s[modDat_1_s$NA_L2NAME %in% c("MIXED WOOD SHIELD", "CENTRAL AND MIXED WOOD PLAINS"), "NA_L2NAME"] <- "CENTRAL AND MIXED WOOD PLAINS AND MIXED WOOD SHIELD"
   
       ## divide southeastern US plains into two regions, since it's by far the largest group
  modDat_1_s[modDat_1_s$NA_L2NAME == "WESTERN CORDILLERA AND UPPER GILA MOUNTAINS" &
               modDat_1_s$Long < -966595#-1773969
               , "NA_L2NAME"] <- "WESTERN CORDILLERA AND UPPER GILA MOUNTAINS 1"
  modDat_1_s[modDat_1_s$NA_L2NAME == "WESTERN CORDILLERA AND UPPER GILA MOUNTAINS", "NA_L2NAME"] <- "WESTERN CORDILLERA AND UPPER GILA MOUNTAINS 2"
   #///
   modDat_1_sf[modDat_1_sf$NA_L2NAME %in% c("MISSISSIPPI ALLUVIAL AND SOUTHEAST USA COASTAL PLAINS", "EVERGLADES"), "NA_L2NAME"] <- "MISSISSIPPI ALLUVIAL AND SOUTHEAST USA COASTAL PLAINS  AND EVERGLADES"
   
   modDat_1_sf[modDat_1_sf$NA_L2NAME %in% c("UPPER GILA MOUNTAINS", "WESTERN CORDILLERA"), "NA_L2NAME"] <- "WESTERN CORDILLERA AND UPPER GILA MOUNTAINS"
   
   modDat_1_sf[modDat_1_sf$NA_L2NAME %in% c("MISSISSIPPI ALLUVIAL AND SOUTHEAST USA COASTAL PLAINS\tAND EVERGLADES", "SOUTHEASTERN USA PLAINS"), "NA_L2NAME"] <- "SOUTHEASTERN USA PLAINS"
   
   modDat_1_sf[modDat_1_sf$NA_L2NAME %in% c("ATLANTIC HIGHLANDS", "OZARK/OUACHITA-APPALACHIAN FORESTS"), "NA_L2NAME"] <- "HIGHLANDS AND APPALACHIAN FORESTS"
   
   modDat_1_sf[modDat_1_sf$NA_L2NAME %in% c("CENTRAL USA PLAINS", "MIXED WOOD PLAINS"), "NA_L2NAME"] <- "CENTRAL AND MIXED WOOD PLAINS"
   
   modDat_1_sf[modDat_1_sf$NA_L2NAME %in% c("MIXED WOOD SHIELD", "CENTRAL AND MIXED WOOD PLAINS"), "NA_L2NAME"] <- "CENTRAL AND MIXED WOOD PLAINS AND MIXED WOOD SHIELD"
          ## divide southeastern US plains into two regions, since it's by far the largest group
  modDat_1_sf[modDat_1_sf$NA_L2NAME == "WESTERN CORDILLERA AND UPPER GILA MOUNTAINS" &
              st_coordinates(modDat_1_sf)[,1] < -966595#-1773969
                , ]$NA_L2NAME <- "WESTERN CORDILLERA AND UPPER GILA MOUNTAINS 1"
  modDat_1_sf[modDat_1_sf$NA_L2NAME == "WESTERN CORDILLERA AND UPPER GILA MOUNTAINS", "NA_L2NAME"] <- "WESTERN CORDILLERA AND UPPER GILA MOUNTAINS 2"
  
  if (response %in% c("C3GramCover_prop", "C4GramCover_prop") ) {
     modDat_1_s[modDat_1_s$NA_L2NAME %in% c("MARINE WEST COAST FOREST", "WESTERN CORDILLERA AND UPPER GILA MOUNTAINS 1"), "NA_L2NAME"] <- "WESTERN CORDILLERA AND UPPER GILA MOUNTAINS 1"
     modDat_1_s[modDat_1_s$NA_L2NAME %in% c("CENTRAL AND MIXED WOOD PLAINS AND MIXED WOOD SHIELD", "HIGHLANDS AND APPALACHIAN FORESTS"), "NA_L2NAME"] <- "CENTRAL AND MIXED WOODS AND HIGHLANDS FORESTS"
     #//
  modDat_1_sf[modDat_1_sf$NA_L2NAME %in% c("MARINE WEST COAST FOREST", "WESTERN CORDILLERA AND UPPER GILA MOUNTAINS 1"), "NA_L2NAME"] <- "WESTERN CORDILLERA AND UPPER GILA MOUNTAINS 1"
  modDat_1_sf[modDat_1_sf$NA_L2NAME %in% c("CENTRAL AND MIXED WOOD PLAINS AND MIXED WOOD SHIELD", "HIGHLANDS AND APPALACHIAN FORESTS"), "NA_L2NAME"] <- "CENTRAL AND MIXED WOODS AND HIGHLANDS FORESTS" 
  
  }
  
} else if (ecoregion == "forest" & response == "CAMCover") {
  
  modDat_1_s[modDat_1_s$NA_L2NAME %in% c("OZARK/OUACHITA-APPALACHIAN FORESTS", "SOUTHEASTERN USA PLAINS"), "NA_L2NAME"] <- "SOUTHEASTERN PLAINS AND APPALACHIAN FORESTS"
    
  modDat_1_s[modDat_1_s$NA_L2NAME %in% c("MARINE WEST COAST FOREST", "WESTERN CORDILLERA"), "NA_L2NAME"] <- "MARINE WEST COAST AND WESTERN CORDILLERA"
    
  modDat_1_s[modDat_1_s$NA_L2NAME %in% c("MIXED WOOD PLAINS", "SOUTHEASTERN PLAINS AND APPALACHIAN FORESTS"), "NA_L2NAME"] <- "SOUTHEASTERN PLAINS AND APPALACHIAN FORESTS"
  
  #///
   modDat_1_sf[modDat_1_sf$NA_L2NAME %in% c("OZARK/OUACHITA-APPALACHIAN FORESTS", "SOUTHEASTERN USA PLAINS"), "NA_L2NAME"] <- "SOUTHEASTERN PLAINS AND APPALACHIAN FORESTS"
    
  modDat_1_sf[modDat_1_sf$NA_L2NAME %in% c("MARINE WEST COAST FOREST", "WESTERN CORDILLERA"), "NA_L2NAME"] <- "MARINE WEST COAST AND WESTERN CORDILLERA"
    
  modDat_1_sf[modDat_1_sf$NA_L2NAME %in% c("MIXED WOOD PLAINS", "SOUTHEASTERN PLAINS AND APPALACHIAN FORESTS"), "NA_L2NAME"] <- "SOUTHEASTERN PLAINS AND APPALACHIAN FORESTS"
  
} else if (ecoregion == "eastForest") {
  modDat_1_s[modDat_1_s$NA_L2NAME %in% c("EVERGLADES", "MISSISSIPPI ALLUVIAL AND SOUTHEAST USA COASTAL PLAINS"), "NA_L2NAME"] <- "EVERGLADES MISSISSIPPI ALLUVIAL AND SOUTHEAST USA COASTAL PLAINS"

  modDat_1_s[modDat_1_s$NA_L2NAME %in% c("MIXED WOOD PLAINS","CENTRAL USA PLAINS"), "NA_L2NAME"] <- "SOUTHEASTERN AND CENTRAL USA PLAINS"

  modDat_1_s[modDat_1_s$NA_L2NAME %in% c("MIXED WOOD SHIELD", "ATLANTIC HIGHLANDS"), "NA_L2NAME"] <- "ATLANTIC HIGHLANDS AND MIXED WOOD SHIELD"

  modDat_1_s[modDat_1_s$NA_L2NAME %in% c("MIXED WOOD PLAINS", "ATLANTIC HIGHLANDS AND MIXED WOOD SHIELD"), "NA_L2NAME"] <- "ATLANTIC HIGHLANDS AND MIXED WOOD SHIELD AND PLAINS"

  modDat_1_s[modDat_1_s$NA_L2NAME %in% c("SOUTHEASTERN AND CENTRAL USA PLAINS", "ATLANTIC HIGHLANDS AND MIXED WOOD SHIELD AND PLAINS"), "NA_L2NAME"] <- "PLAINS AND HIGHLANDS AND SHIELD"

  modDat_1_s[modDat_1_s$NA_L2NAME %in% c("EVERGLADES MISSISSIPPI ALLUVIAL AND SOUTHEAST USA COASTAL PLAINS", "SOUTHEASTERN USA PLAINS"), "NA_L2NAME"] <- "SOUTHEASTERN PLAINS AND COAST"

  # #////
   modDat_1_sf[modDat_1_sf$NA_L2NAME %in% c("EVERGLADES", "MISSISSIPPI ALLUVIAL AND SOUTHEAST USA COASTAL PLAINS"), "NA_L2NAME"] <- "EVERGLADES MISSISSIPPI ALLUVIAL AND SOUTHEAST USA COASTAL PLAINS"

   modDat_1_sf[modDat_1_sf$NA_L2NAME %in% c("MIXED WOOD PLAINS","CENTRAL USA PLAINS"), "NA_L2NAME"] <- "SOUTHEASTERN AND CENTRAL USA PLAINS"
  
   modDat_1_sf[modDat_1_sf$NA_L2NAME %in% c("MIXED WOOD SHIELD", "ATLANTIC HIGHLANDS"), "NA_L2NAME"] <- "ATLANTIC HIGHLANDS AND MIXED WOOD SHIELD"
  
   modDat_1_sf[modDat_1_sf$NA_L2NAME %in% c("MIXED WOOD PLAINS", "ATLANTIC HIGHLANDS AND MIXED WOOD SHIELD"), "NA_L2NAME"] <- "ATLANTIC HIGHLANDS AND MIXED WOOD SHIELD AND PLAINS"
  
   modDat_1_sf[modDat_1_sf$NA_L2NAME %in% c("SOUTHEASTERN AND CENTRAL USA PLAINS", "ATLANTIC HIGHLANDS AND MIXED WOOD SHIELD AND PLAINS"), "NA_L2NAME"] <- "PLAINS AND HIGHLANDS AND SHIELD"
  
   modDat_1_sf[modDat_1_sf$NA_L2NAME %in% c("EVERGLADES MISSISSIPPI ALLUVIAL AND SOUTHEAST USA COASTAL PLAINS", "SOUTHEASTERN USA PLAINS"), "NA_L2NAME"] <- "SOUTHEASTERN PLAINS AND COAST"
  
   ## divide southeastern US plains into two regions, since it's by far the largest group
  # modDat_1_s[modDat_1_s$NA_L2NAME == "SOUTHEASTERN USA PLAINS" &
  #              modDat_1_s$Lat < -590062, "NA_L2NAME"] <- "SOUTHEASTERN USA PLAINS 1"
  # modDat_1_s[modDat_1_s$NA_L2NAME == "SOUTHEASTERN USA PLAINS", #&
  #             # modDat_1_s$Lat < -590062,
  #            "NA_L2NAME"] <- "SOUTHEASTERN USA PLAINS 2"

  #   ## divide southeastern US plains into two regions, since it's by far the largest group
  # modDat_1_s[modDat_1_s$NA_L2NAME == "OZARK/OUACHITA-APPALACHIAN FORESTS" &
  #              modDat_1_s$Long < 854862.2, "NA_L2NAME"] <- "OZARK/OUACHITA-APPALACHIAN FORESTS 1"
  # modDat_1_s[modDat_1_s$NA_L2NAME == "OZARK/OUACHITA-APPALACHIAN FORESTS" &
  #              modDat_1_s$Long  >=   854862.2, "NA_L2NAME"] <- "OZARK/OUACHITA-APPALACHIAN FORESTS 2"
}
# make a table of n for each region
modDat_1_s %>% 
  group_by(NA_L2NAME) %>% 
  dplyr::summarize("Number_Of_Observations" = length(NA_L2NAME)) %>% 
  rename("Level_2_Ecoregion" = NA_L2NAME)%>% 
  kable() %>%
kable_styling(bootstrap_options = c("striped", "hover", "condensed")) 
Level_2_Ecoregion Number_Of_Observations
ATLANTIC HIGHLANDS 15019
CENTRAL USA PLAINS 22179
COLD DESERTS 89534
MEDITERRANEAN CALIFORNIA AND UPPER GILA MOUNTAINS 22555
MIXED WOOD SHIELD 20318
SOUTH CENTRAL SEMIARID PRAIRIES 102278
SOUTHEASTERN AND MIXED WOOD PLAINS 225363
TAMAULIPAS-TEXAS SEMIARID PLAIN 5700
TEMPERATE PRAIRIES 51186
WARM DESERTS 38782
WEST-CENTRAL SEMIARID PRAIRIES 56596
WESTERN CORDILLERA AND WEST COAST FOREST 78800
WESTERN SIERRA MADRE PIEDMONT 3808

Then, look at the spatial distribution and environmental characteristics of the grouped ecoregions

map1 <- ggplot() +
  geom_sf(data=cropped_states,fill='white') +
  geom_sf(data=modDat_1_sf#[modDat_1_sf$NA_L2NAME %in% c("MIXED WOOD PLAINS"),]
          ,
          aes(fill=as.factor(NA_L2NAME)),linewidth=0.5,alpha=0.5) +
  geom_point(data=modDat_1_s#[modDat_1_s$NA_L2NAME %in% c("MIXED WOOD PLAINS"),]
             ,
             alpha=0.5, 
             aes(x = Long, y = Lat, color=as.factor(NA_L2NAME)), alpha = .1) +
  theme(legend.position = 'none') +
  labs(title = "Level 2 Ecoregions as spatial blocks")

hull <- modDat_1_sf %>%
  ungroup() %>%
  group_by(NA_L2NAME) %>%
  slice(chull(tmean, prcp))

plot1<-ggplot(data=modDat_1_sf,aes(x=tmean,y=prcp)) +
  geom_polygon(data = hull, alpha = 0.25,aes(fill=NA_L2NAME) )+
  geom_point(aes(group=NA_L2NAME,color=NA_L2NAME),alpha=0.25) +
  theme_minimal() + xlab("Annual Average T_mean - long-term average") +
  ylab("Annual Average Precip - long-term average") 

plot2<-ggplot(data=modDat_1_sf %>%
                pivot_longer(cols=tmean:prcp),
              aes(x=value,group=name)) +
  # geom_polygon(data = hull, alpha = 0.25,aes(fill=fold) )+
  geom_density(aes(group=NA_L2NAME,fill=NA_L2NAME),alpha=0.25) +
  theme_minimal() +
  facet_wrap(~name,scales='free')
 
library(patchwork)
(combo <- (map1+plot1)/plot2) 

Fit a global model with all of the data

First, fit a LASSO regression model using the glmnet R package

  • This regression is a Gamma glm with a log link
  • Use cross validation across level 2 ecoregions to tune the lambda parameter in the LASSO model
  • this model is fit to using the scaled weather/climate/soils variables
  • this list of possible predictors includes:
    1. main effects
    2. interactions between all soils variables
    3. interactions between climate and weather variables
    4. transformed main effects (squared, log-transformed (add a uniform integer – 20– to all variables prior to log-transformation), square root-transformed (add a uniform integer – 20– to all variables prior to log-transformation))

Get rid of transformed predictions and interactions that are correlated

# get first pass of names correlated variables
X_df <- X %>% 
  as.data.frame() %>% 
  dplyr::select(-'(Intercept)')  
corrNames_i <- X_df %>% 
  cor()  %>% 
   caret::findCorrelation(cutoff = .7, verbose = FALSE, names = TRUE, exact = TRUE)
# remove those names that are untransformed main effects 
  # vector of columns to remove 
badNames <- corrNames_i[!(corrNames_i %in% prednames)]
while (sum(!(corrNames_i %in% prednames))>0) {
 corrNames_i <-  X_df %>% 
    dplyr::select(-badNames) %>% 
     cor()  %>% 
   caret::findCorrelation(cutoff = .7, verbose = FALSE, names = TRUE, exact = TRUE)
 # update the vector of names to remove 
 badNames <- unique(c(badNames, corrNames_i[!(corrNames_i %in% prednames)]))
}

## see if there are any correlated variables left (would be all main effects at this point)
# if there are, step through and remove the variable that each is most correlated with 
if (length(corrNames_i)>1) {
  for (i in 1:length(corrNames_i)) {
    X_i <- X_df %>% 
      dplyr::select(-badNames)
    if (corrNames_i[i] %in% names(X_i)) {
    corMat_i <- cor(x = X_i[corrNames_i[i]], y = X_i %>% dplyr::select(-corrNames_i[i])) 
    badNames_i <- colnames(corMat_i)[abs(corMat_i)>=.7]
    # if there are any predictors in the 'badNames_i', remove them from this list
    if (length(badNames_i) > 0 & sum(c(badNames_i %in% prednames))>0) {
        badNames_i <- badNames_i[!(badNames_i %in% prednames)]
    }
    badNames <- unique(c(badNames, badNames_i))
    }
  }
}
## update the X matrix to exclude these correlated variables
X <- X[,!(colnames(X) %in% badNames)]
if (autoKfold == FALSE) {
  # get the ecoregions for training lambda
  train_eco <- modDat_1_s$NA_L2NAME#[train]
  
  # Fit model -----------------------------------------------
  # specify leave-one-year-out cross-validation
  my_folds <- as.numeric(as.factor(train_eco))

  if (run == TRUE) {
    # set up parallel processing
    library(doMC)
    # this computer has 16 cores (parallel::detectCores())
    registerDoMC(cores = 8)
    
    fit <- cv.glmnet(
    x = X[,2:ncol(X)], 
    y = y, 
    family = stats::Gamma(link = "log"),
    keep = FALSE,
    alpha = 1,  # 0 == ridge regression, 1 == lasso, 0.5 ~~ elastic net
    #lambda = lambdas, 
    nlambda = 50,
    type.measure="mse",
    #penalty.factor = pen_facts,
    foldid = my_folds,
    #thresh = thresh,
    standardize = FALSE, ## scales variables prior to the model sequence... coefficients are always returned on the original scale
    parallel = TRUE#, 
    #relax = ifelse(response == "ShrubCover", yes = TRUE, no = FALSE)
    )
    base::saveRDS(fit, paste0("/Users/astears/Documents/Dropbox_static/Work/NAU_USGS_postdoc/PED_vegClimModels/Analysis/BiomassQuantity/Analysis/models/", response, "_globalLASSOmod_gammaLogLink_",ecoregion,".rds"))
  
  } else {
    fit <- readRDS(paste0("/Users/astears/Documents/Dropbox_static/Work/NAU_USGS_postdoc/PED_vegClimModels/Analysis/BiomassQuantity/Analysis/models/", response, "_globalLASSOmod_gammaLogLink_",ecoregion, ".rds"))
  }
  
} else if (autoKfold == TRUE) {
   if (run == TRUE) {
    # set up parallel processing
    library(doMC)
    # this computer has 16 cores (parallel::detectCores())
    registerDoMC(cores = 8)
    
    fit <- cv.glmnet(
    x = X[,2:ncol(X)], 
    y = y, 
    family = stats::Gamma(link = "log"),
    keep = FALSE,
    alpha = .5,  # 0 == ridge regression, 1 == lasso, 0.5 ~~ elastic net
    lambda = lambdas,
    relax = ifelse(response == "ShrubCover", yes = TRUE, no = FALSE),
    #nlambda = 100,
    type.measure="mse",
    #penalty.factor = pen_facts,
    #foldid = my_folds,
    #thresh = thresh,
    standardize = FALSE, ## scales variables prior to the model sequence... coefficients are always returned on the original scale
    parallel = TRUE
    )
    base::saveRDS(fit, paste0("/Users/astears/Documents/Dropbox_static/Work/NAU_USGS_postdoc/PED_vegClimModels/Analysis/BiomassQuantity/Analysis/models/", response, "_globalLASSOmod_gammaLogLink_",ecoregion, "_kFoldDefault.rds"))
  
  } else {
    fit <- readRDS(paste0("/Users/astears/Documents/Dropbox_static/Work/NAU_USGS_postdoc/PED_vegClimModels/Analysis/BiomassQuantity/Analysis/models/", response, "_globalLASSOmod_gammaLogLink_",ecoregion, "_kFoldDefault.rds"))
  }
}

  # assess model fit
  # assess.glmnet(fit$fit.preval, #newx = X[,2:293], 
  #               newy = y, family = stats::Gamma(link = "log"))
  # save the minimum lambda
  best_lambda <- fit$lambda.min
  # save the lambda for the most regularized model w/ an MSE that is still 1SE w/in the best lambda model
  lambda_1SE <- fit$lambda.1se
  # save the lambda for the most regularized model w/ an MSE that is still .5SE w/in the best lambda model
  lambda_halfSE <- best_lambda + ((lambda_1SE - best_lambda)/2)
 
  print(fit)     
## 
## Call:  cv.glmnet(x = X[, 2:ncol(X)], y = y, type.measure = "mse", foldid = my_folds,      keep = FALSE, parallel = TRUE, family = stats::Gamma(link = "log"),      alpha = 1, nlambda = 50, standardize = FALSE) 
## 
## Measure: Mean-Squared Error 
## 
##     Lambda Index Measure     SE Nonzero
## min 0.1666    11    2453  967.3      10
## 1se 0.6211     4    3416 1165.5       1
  plot(fit)

Now, we need to do stability selection to ensure the coefficients that are being chosen with each lambda are stable

## stability selection for best lambda model 
# setup params
p <- ncol(X[,2:ncol(X)]) # of parameters
n <- length(y) # of observations
n_iter <- 100        # number of subsamples
sample_frac <- 0.75  # fraction of data to subsample
lambda_val <- best_lambda    # fixed lambda value (could be chosen via CV)

# Track selection
selection_counts <- matrix(0, nrow = p, ncol = 1)

for (i in 1:n_iter) {
  # Subsample rows
  sample_idx <- sample(1:n, size = floor(sample_frac * n), replace = FALSE)
  X_sub <- X[sample_idx, ]
  y_sub <- y[sample_idx]

  # Fit Lasso model
  fit_stab_i <- glmnet(x = X_sub[,2:ncol(X_sub)], y = y_sub, 
    family = stats::Gamma(link = "log"),
    alpha = 1, lambda = lambda_val, standardize = FALSE)

  # Get non-zero coefficients (excluding intercept)
  selected <- which(as.vector(coef(fit_stab_i))[-1] != 0)
  selection_counts[selected] <- selection_counts[selected] + 1
}

# Convert counts to selection probabilities (the probability that a variable is selected over 100 iterations)
selection_prob <- selection_counts / n_iter
selection_prob_df <- data.frame(
  VariableNumber = paste0("X", 1:p),
  VariableName = rownames(coef(fit_stab_i))[2:(p+1)],
  SelectionProb = as.vector(selection_prob)
)

# get those variables that are selected in ≥70% of subsets (Meinshausen and Bühlmann, 2010)
bestLambda_coef <- selection_prob_df[selection_prob_df$SelectionProb>=.7, c("VariableName", "SelectionProb")]

#//////
# stability selection for 1se lambda model
lambda_val <-  lambda_1SE    # fixed lambda value (could be chosen via CV)

# Track selection
selection_counts <- matrix(0, nrow = p, ncol = 1)

for (i in 1:n_iter) {
  # Subsample rows
  sample_idx <- sample(1:n, size = floor(sample_frac * n), replace = FALSE)
  X_sub <- X[sample_idx, ]
  y_sub <- y[sample_idx]

  # Fit Lasso model
  fit_stab_i <- glmnet(x = X_sub[,2:ncol(X_sub)], y = y_sub, 
    family = stats::Gamma(link = "log"),
    alpha = 1, lambda = lambda_val, standardize = FALSE)

  # Get non-zero coefficients (excluding intercept)
  selected <- which(as.vector(coef(fit_stab_i))[-1] != 0)
  selection_counts[selected] <- selection_counts[selected] + 1
}

# Convert counts to selection probabilities (the probability that a variable is selected over 100 iterations)
selection_prob <- selection_counts / n_iter
selection_prob_df <- data.frame(
  VariableNumber = paste0("X", 1:p),
  VariableName = rownames(coef(fit_stab_i))[2:(p+1)],
  SelectionProb = as.vector(selection_prob)
)

# get those variables that are selected in ≥70% of subsets (Meinshausen and Bühlmann, 2010)
seLambda_coef <- selection_prob_df[selection_prob_df$SelectionProb>=.7, c("VariableName", "SelectionProb")]

# #//////
# stability selection for half se lambda model
lambda_val <- lambda_halfSE    # fixed lambda value (could be chosen via CV)

# Track selection
selection_counts <- matrix(0, nrow = p, ncol = 1)

for (i in 1:n_iter) {
  # Subsample rows
  sample_idx <- sample(1:n, size = floor(sample_frac * n), replace = FALSE)
  X_sub <- X[sample_idx, ]
  y_sub <- y[sample_idx]

  # Fit Lasso model
  fit_stab_i <- glmnet(x = X_sub[,2:ncol(X_sub)], y = y_sub,
    family = stats::Gamma(link = "log"),
    alpha = 1, lambda = lambda_val, standardize = FALSE)

  # Get non-zero coefficients (excluding intercept)
  selected <- which(as.vector(coef(fit_stab_i))[-1] != 0)
  selection_counts[selected] <- selection_counts[selected] + 1
}

# Convert counts to selection probabilities (the probability that a variable is selected over 100 iterations)
selection_prob <- selection_counts / n_iter
selection_prob_df <- data.frame(
  VariableNumber = paste0("X", 1:p),
  VariableName = rownames(coef(fit_stab_i))[2:(p+1)],
  SelectionProb = as.vector(selection_prob)
)

# get those variables that are selected in ≥70% of subsets (Meinshausen and Bühlmann, 2010)
halfseLambda_coef <- selection_prob_df[selection_prob_df$SelectionProb>=.7, c("VariableName", "SelectionProb")]

If prompted to do so by the input arguments, remove any predictors that are for weather anomalies whose corresponding climate predictor is not included in the model

# if (trimAnom == TRUE) {
#   # get unique predictors
#   bestLamb_all <- bestLambda_coef$VariableName %>% #[str_detect(bestLambda_coef$VariableName, pattern = "_anom_s")] %>% 
#     str_remove(pattern = "I\\(") %>% 
#     str_remove(pattern = "\\^2\\)") %>% 
#     str_remove(pattern = "\\^2\\)") %>% 
#     str_split(pattern = ":", simplify = TRUE) 
#   if (ncol(bestLamb_all) == 1) {
#     bestLamb_all <- unique(bestLamb_all)
#   } else {
#     bestLamb_all <-  c(bestLamb_all[bestLamb_all[,1] !="",1], bestLamb_all[bestLamb_all[,2] !="",2]) %>% 
#       unique()
#   }
#   # get anomalies
#    bestLamb_anom <- bestLamb_all[bestLamb_all %in% prednames_weath]
#   # get climate
#    bestLamb_clim <- bestLamb_all[bestLamb_all %in% prednames_clim]
#   # which anomalies are present in the predictors, but their corresponding climate variable isn't
#    bestLamb_anomsWithMissingClim <- bestLamb_anom[!(str_remove(bestLamb_anom, "_anom") %in% bestLamb_clim)]
#    # remove anomalies (and all interaction terms w/ those anomalies) from the predictor list
# 
#    if (length(bestLamb_anomsWithMissingClim) != 0) {
#    
#         bestLambda_coef_NEW <- bestLambda_coef
#       for (i in 1:length(bestLamb_anomsWithMissingClim)) {
#      bestLambda_coef_NEW <- bestLambda_coef_NEW[!str_detect(bestLambda_coef_NEW$VariableName, pattern = bestLamb_anomsWithMissingClim[i]),]
#       }
#      
#    bestLambda_coef <- bestLambda_coef_NEW
#    }
#    
#    
#   #//// 1 se lambda model
#       if (nrow(seLambda_coef) !=0) {
#         # get unique predictors
#   seLamb_all <- seLambda_coef$VariableName %>% #[str_detect(seLambda_coef$VariableName, pattern = "_anom_s")] %>% 
#     str_remove(pattern = "I\\(") %>% 
#     str_remove(pattern = "_s\\^2\\)") %>% 
#     str_remove(pattern = "\\^2\\)") %>% 
#     str_split(pattern = ":", simplify = TRUE) 
#   if (ncol(seLamb_all) == 1) {
#     seLamb_all <- unique(seLamb_all)
#   } else {
#     seLamb_all <-  c(seLamb_all[seLamb_all[,1] !="",1], seLamb_all[seLamb_all[,2] !="",2]) %>% 
#       unique()
#   }
#   # get anomalies
#    seLamb_anom <- seLamb_all[seLamb_all %in% prednames_weath]
#   # get climate
#    seLamb_clim <- seLamb_all[seLamb_all %in% prednames_clim]
#   # which anomalies are present in the predictors, but their corresponding climate variable isn't
#    seLamb_anomsWithMissingClim <- seLamb_anom[!(str_remove(seLamb_anom, "_anom") %in%  seLamb_clim)]
#    # remove anomalies (and all interaction terms w/ those anomalies) from the predictor list
#       if (length(seLamb_anomsWithMissingClim) != 0) {
#     seLambda_coef_NEW <- seLambda_coef
#    for (i in 1:length(seLamb_anomsWithMissingClim)) {
#      seLambda_coef_NEW <- seLambda_coef_NEW[!str_detect(seLambda_coef_NEW$VariableName, pattern = seLamb_anomsWithMissingClim[i]),]
#    }
#    seLambda_coef <- seLambda_coef_NEW
#       }
#    }
#   
#   #//// 1 se lambda model
#       if (nrow(halfseLambda_coef) !=0) {
#         # get unique predictors
#   halfseLamball<- halfseLambda_coef$VariableName %>% #[str_detect(halfseLambda_coef$VariableName, pattern = "_anom_s")] %>% 
#     str_remove(pattern = "I\\(") %>% 
#     str_remove(pattern = "_s\\^2\\)") %>% 
#     str_split(pattern = ":", simplify = TRUE) 
#   
#     if (ncol(halfseLamball) == 1) {
#     halfseLamball <- unique(halfseLamball)
#   } else {
#     halfseLamball <-  c(halfseLamball[halfseLamball[,1] !="",1], halfseLamball[halfseLamball[,2] !="",2]) %>% 
#       unique()
#   }
#   
#   # get anomalies
#    halfseLambanom <- halfseLamball[halfseLamball %in% prednames_weath]
#   # get climate
#    halfseLambclim <- halfseLamball[halfseLamball %in% prednames_clim]
#   # which anomalies are present in the predictors, but their corresponding climate variable isn't
#    halfseLambanomsWithMissingClim <- halfseLambanom[!(str_remove(halfseLambanom, "_anom_s") %in%  halfseLambclim)]
#    # remove anomalies (and all interaction terms w/ those anomalies) from the predictor list
# 
#    
#    ##
#         if (length(halfseLambanomsWithMissingClim) != 0) {
#    halfseLambda_coef_NEW <- halfseLambda_coef
#    for (i in 1:length(halfseLambanomsWithMissingClim)) {
#      halfseLambda_coef_NEW <- halfseLambda_coef_NEW[!str_detect(halfseLambda_coef_NEW$VariableName, pattern = halfseLambanomsWithMissingClim[i]),]
#    }
#    halfseLambda_coef <- halfseLambda_coef_NEW
#       }
#    }
#     ##
#   
#       }

Then, fit regular glm models (Gamma glm with a log link), first using the coefficients from the ‘best’ lambda identified in the LASSO model, and then using the coefficients from the ‘1SE’ lambda and then the ‘1/2SE’ lambda values identified from the LASSO (this is the value of lambda such that the cross validation error is within 1 standard error of the minimum).

## fit w/ the identified coefficients from the 'best' lambda, but using the glm function
  mat_glmnet_best <- bestLambda_coef$VariableName 

  if (length(mat_glmnet_best) == 0) {
    f_glm_bestLambda <- as.formula(paste0("response_transformed ~  1"))
  } else {
  f_glm_bestLambda <- as.formula(paste0( "response_transformed ~ ", paste0(mat_glmnet_best, collapse = " + ")))
  }
  
  fit_glm_bestLambda <- glm(data = modDat_1_s
                              , formula =  f_glm_bestLambda, family =  stats::Gamma(link = "log"))
  
   ## fit w/ the identified coefficients from the '1se' lambda, but using the glm function
  mat_glmnet_1se <- seLambda_coef$VariableName

  if (length(mat_glmnet_1se) == 0) {
    f_glm_1se <- as.formula(paste0("response_transformed ~  1"))
  } else {
  f_glm_1se <- as.formula(paste0("response_transformed ~ ", paste0(mat_glmnet_1se, collapse = " + ")))
  }


  fit_glm_se <- glm(data = modDat_1_s, formula = f_glm_1se,
                    family =  stats::Gamma(link = "log"))

     ## fit w/ the identified coefficients from the '.5se' lambda, but using the glm function
  mat_glmnet_halfse <- halfseLambda_coef$VariableName

  if (length(mat_glmnet_halfse) == 0) {
    f_glm_halfse <- as.formula(paste0(response, "response_transformed ~  1"))
  } else {
  f_glm_halfse <- as.formula(paste0("response_transformed ~" , paste0(mat_glmnet_halfse, collapse = " + ")))
  }

  fit_glm_halfse <- glm(data = modDat_1_s, formula =  f_glm_halfse,
                    family =  stats::Gamma(link = "log"))

  ## save models 
  if (trimAnom == TRUE) {
    saveRDS(fit_glm_bestLambda, paste0("/Users/astears/Documents/Dropbox_static/Work/NAU_USGS_postdoc/PED_vegClimModels/Analysis/BiomassQuantity/Analysis/models/",response,"_",ecoregion, "_bestLambdaGLM.rds"))
  saveRDS(fit_glm_halfse, paste0("/Users/astears/Documents/Dropbox_static/Work/NAU_USGS_postdoc/PED_vegClimModels/Analysis/BiomassQuantity/Analysis/models/",response,"_",ecoregion, "_halfSELambdaGLM.rds"))
  saveRDS(fit_glm_se, paste0("/Users/astears/Documents/Dropbox_static/Work/NAU_USGS_postdoc/PED_vegClimModels/Analysis/BiomassQuantity/Analysis/models/",response,"_",ecoregion, "_oneSELambdaGLM.rds"))
  } else {
    saveRDS(fit_glm_bestLambda, paste0("/Users/astears/Documents/Dropbox_static/Work/NAU_USGS_postdoc/PED_vegClimModels/Analysis/BiomassQuantity/Analysis/models/",response,"_",ecoregion, "_noTLP_",removeTLP,"_bestLambdaGLM.rds"))
  saveRDS(fit_glm_halfse, paste0("/Users/astears/Documents/Dropbox_static/Work/NAU_USGS_postdoc/PED_vegClimModels/Analysis/BiomassQuantity/Analysis/models/",response,"_",ecoregion, "_noTLP_",removeTLP,"_halfSELambdaGLM.rds"))
  saveRDS(fit_glm_se, paste0("/Users/astears/Documents/Dropbox_static/Work/NAU_USGS_postdoc/PED_vegClimModels/Analysis/BiomassQuantity/Analysis/models/",response,"_",ecoregion, "_noTLP_",removeTLP,"_oneSELambdaGLM.rds"))
    
  }

Then, we predict (on the training set) using both of these models (best lambda and 1se lambda)

  ## predict on the test data
  # lasso model predictions with the optimal lambda
  optimal_pred <- predict(fit_glm_bestLambda, newx=X[,2:ncol(X)], type = "response") -2
  optimal_pred_1se <-  predict(fit_glm_se, newx=X[,2:ncol(X)], type = "response") -2
  optimal_pred_halfse <- predict(fit_glm_halfse, newx = X[,2:ncol(X)], type = "response") -2
  
    null_fit <- glm(#data = data.frame("y" = y, X[,paste0(prednames, "_s")]), 
      formula = y ~ 1, family = stats::Gamma(link = "log"))
  null_pred <- predict(null_fit, newdata = as.data.frame(X), type = "response"
                       ) -2

  # ## snap values above 100 and below 0 to be 100 or z
  # #optimal_pred[optimal_pred>100] <- 100
  # optimal_pred[optimal_pred<0] <- 0
  # #optimal_pred_1se[optimal_pred_1se>100] <- 100
  # optimal_pred_1se[optimal_pred_1se<0] <- 0
  # #optimal_pred_halfse[optimal_pred_halfse>100] <- 100
  # optimal_pred_halfse[optimal_pred_halfse<0] <- 0
  # 
  # save data
  fullModOut <- list(
    "modelObject" = fit,
    "nullModelObject" = null_fit,
    "modelPredictions" = data.frame(#ecoRegion_holdout = rep(test_eco,length(y)),
      obs=y-2,
                    pred_opt=optimal_pred, 
                    pred_opt_se = optimal_pred_1se,
                    pred_opt_halfse = optimal_pred_halfse,
                    pred_null=null_pred#,
                    #pred_nopenalty=nopen_pred
                    ))
  
# # calculate correlations between null and optimal model 
# my_cors <- c(cor(optimal_pred, c(y)),
#              cor(optimal_pred_1se, c(y)), 
#             cor(null_pred, c(y))
#             )
# 
# # calculate mse between null and optimal model 
# my_mse <- c(mean((fullModOut$modelPredictions$pred_opt -  c(y))^2) ,
#             mean((fullModOut$modelPredictions$pred_opt_se -  c(y))^2) ,
#             mean((fullModOut$modelPredictions$pred_null - c(y))^2)#,
#             #mean((obs_pred$pred_nopenalty - obs_pred$obs)^2)
#             )

ggplot() + 
  geom_point(aes(X[,2], fullModOut$modelPredictions$obs), col = "black", alpha = .1) + 
  geom_point(aes(X[,2], fullModOut$modelPredictions$pred_opt), col = "red", alpha = .1) + ## predictions w/ the CV model
  geom_point(aes(X[,2], fullModOut$modelPredictions$pred_opt_halfse), col = "orange", alpha = .1) + ## predictions w/ the CV model (.5se lambda)
  geom_point(aes(X[,2], fullModOut$modelPredictions$pred_opt_se), col = "green", alpha = .1) + ## predictions w/ the CV model (1se lambda)
  geom_point(aes(X[,2], fullModOut$modelPredictions$pred_null), col = "blue", alpha = .1) + 
  labs(title = "A rough comparison of observed and model-predicted values", 
       subtitle = "black = observed values \n red = predictions from 'best lambda' model \n orange = predictions for '1/2se' lambda model \n green = predictions from '1se' lambda model \n blue = predictions from null model") +
  xlab(colnames(X)[2])

  #ylim(c(0,200))

The internal cross-validation process to fit the global LASSO model identified an optimal lambda value (regularization parameter) of r{print(best_lambda)}. The lambda value such that the cross validation error is within 1 standard error of the minimum (“1se lambda”) was `r{print(fit$lambda.1se)}`` . The following coefficients were kept in each model:

# the coefficient matrix from the 'best model' -- find and print those coefficients that aren't 0 in a table
coef_glm_bestLambda <- coef(fit_glm_bestLambda) %>% 
  data.frame() 
coef_glm_bestLambda$coefficientName <- rownames(coef_glm_bestLambda)
names(coef_glm_bestLambda)[1] <- "coefficientValue_bestLambda"
# coefficient matrix from the '1se' model 
coef_glm_1se <- coef(fit_glm_se) %>% 
  data.frame() 
coef_glm_1se$coefficientName <- rownames(coef_glm_1se)
names(coef_glm_1se)[1] <- "coefficientValue_1seLambda"
# coefficient matrix from the 'half se' model 
coef_glm_halfse <- coef(fit_glm_halfse) %>% 
  data.frame() 
coef_glm_halfse$coefficientName <- rownames(coef_glm_halfse)
names(coef_glm_halfse)[1] <- "coefficientValue_halfseLambda"
# add together
coefs <- full_join(coef_glm_bestLambda, coef_glm_halfse) %>% 
  full_join(coef_glm_1se) %>% 
  dplyr::select(coefficientName, coefficientValue_bestLambda,
                coefficientValue_halfseLambda, coefficientValue_1seLambda)

globModTerms <- coefs[!is.na(coefs$coefficientValue_bestLambda), "coefficientName"]

## also, get the number of unique variables in each model 
var_prop_pred <- paste0("biomass_MgPerHect", "_pred")
response_vars <- c("biomass_MgPerHect", var_prop_pred)
# for best lambda model
prednames_fig <- paste(str_split(globModTerms, ":", simplify = TRUE)) 
prednames_fig <- str_replace(prednames_fig, "I\\(", "")
prednames_fig <- str_replace(prednames_fig, "\\^2\\)", "")
prednames_fig <- unique(prednames_fig[prednames_fig>0])
prednames_fig <- prednames_fig
prednames_fig_num <- length(prednames_fig)
# for 1SE lambda model
globModTerms_1se <- coefs[!is.na(coefs$coefficientValue_1seLambda), "coefficientName"]
if (length(globModTerms_1se) == 1) {
prednames_fig_1se <- paste(str_split(globModTerms_1se, ":", simplify = TRUE)) 
prednames_fig_1se <- str_replace(prednames_fig_1se, "I\\(", "")
prednames_fig_1se <- str_replace(prednames_fig_1se, "\\^2\\)", "")
prednames_fig_1se <- unique(prednames_fig_1se[prednames_fig_1se>0])
prednames_fig_1se_num <- c(0)
} else {
prednames_fig_1se <- paste(str_split(globModTerms_1se, ":", simplify = TRUE)) 
prednames_fig_1se <- str_replace(prednames_fig_1se, "I\\(", "")
prednames_fig_1se <- str_replace(prednames_fig_1se, "\\^2\\)", "")
prednames_fig_1se <- unique(prednames_fig_1se[prednames_fig_1se>0])
prednames_fig_1se_num <- length(prednames_fig_1se)
}
# for 1/2SE lambda model
globModTerms_halfse <- coefs[!is.na(coefs$coefficientValue_halfseLambda), "coefficientName"]
if (length(globModTerms_halfse) == 1) {
prednames_fig_halfse <- paste(str_split(globModTerms_halfse, ":", simplify = TRUE)) 
prednames_fig_halfse <- str_replace(prednames_fig_halfse, "I\\(", "")
prednames_fig_halfse <- str_replace(prednames_fig_halfse, "\\^2\\)", "")
prednames_fig_halfse <- unique(prednames_fig_halfse[prednames_fig_halfse>0])
prednames_fig_halfse_num <- c(0)
} else {
prednames_fig_halfse <- paste(str_split(globModTerms_halfse, ":", simplify = TRUE)) 
prednames_fig_halfse <- str_replace(prednames_fig_halfse, "I\\(", "")
prednames_fig_halfse <- str_replace(prednames_fig_halfse, "\\^2\\)", "")
prednames_fig_halfse <- unique(prednames_fig_halfse[prednames_fig_halfse>0])
prednames_fig_halfse_num <- length(prednames_fig_halfse)
}
# make a table
kable(coefs, col.names = c("Coefficient Name", "Value from best lambda model", 
                           "Value form 1/2 se lambda", "Value from 1se lambda model")
      ) %>%
kable_styling(bootstrap_options = c("striped", "hover", "condensed")) 
Coefficient Name Value from best lambda model Value form 1/2 se lambda Value from 1se lambda model
(Intercept) 3.0721735 3.1259997 3.2674852
prcpTempCorr -0.2734698 NA NA
prcp 0.6132593 0.8044338 0.9106543
prcp_seasonality -0.2775618 NA NA
prcp_dry 0.1421248 0.0558819 NA
t_warm -0.1629323 -0.3743180 NA
coarse 0.0313990 NA NA
AWHC -0.2662962 NA NA
clay -0.1652599 NA NA
carbon 0.0653100 0.1233390 NA
prcp_seasonality:prcp_wet 0.1786602 NA NA
# calculate RMSE of all models 
RMSE_best <- yardstick::rmse(fullModOut$modelPredictions[,c("obs", "pred_opt")], truth = "obs", estimate = "pred_opt")$.estimate
RMSE_halfse <- yardstick::rmse(fullModOut$modelPredictions[,c("obs", "pred_opt_halfse")], truth = "obs", estimate = "pred_opt_halfse")$.estimate
RMSE_1se <- yardstick::rmse(fullModOut$modelPredictions[,c("obs", "pred_opt_se")], truth = "obs", estimate = "pred_opt_se")$.estimate
# calculate bias of all models
bias_best <-  mean((fullModOut$modelPredictions$obs) - fullModOut$modelPredictions$pred_opt)
bias_halfse <-  mean((fullModOut$modelPredictions$obs) - fullModOut$modelPredictions$pred_opt_halfse)
bias_1se <- mean((fullModOut$modelPredictions$obs) - fullModOut$modelPredictions$pred_opt_se)

uniqueCoeffs <- data.frame("Best lambda model" = c(RMSE_best, bias_best,
  as.integer(length(globModTerms)-1), as.integer(prednames_fig_num), 
                                                   as.integer(sum(prednames_fig %in% c(prednames_clim))),
                                                   #as.integer(sum(prednames_fig %in% c(prednames_weath))),
                                                   as.integer(sum(prednames_fig %in% c(prednames_soils)))
                                                   ), 
                           "1/2 se lambda model" = c(RMSE_halfse, bias_halfse,
                             length(globModTerms_halfse)-1, prednames_fig_halfse_num,
                                                   sum(prednames_fig_halfse %in% c(prednames_clim)),
                                                   #sum(prednames_fig_halfse %in% c(prednames_weath)),
                                                   sum(prednames_fig_halfse %in% c(prednames_soils))), 
                           "1se lambda model" = c(RMSE_1se, bias_1se,
                             length(globModTerms_1se)-1, prednames_fig_1se_num,
                                                   sum(prednames_fig_1se %in% c(prednames_clim)),
                                                   #sum(prednames_fig_1se %in% c(prednames_weath)),
                                                   sum(prednames_fig_1se %in% c(prednames_soils))))
row.names(uniqueCoeffs) <- c("RMSE", "bias: mean(obs-pred.)", "Total number of coefficients", "Number of unique coefficients",
                             "Number of unique climate coefficients", 
                             "Number of unique soils coefficients"
                             )

kable(uniqueCoeffs, 
      col.names = c("Best lambda model", "1/2 se lambda model", "1se lambda model"), row.names = TRUE) %>%
kable_styling(bootstrap_options = c("striped", "hover", "condensed")) 
Best lambda model 1/2 se lambda model 1se lambda model
RMSE 207.42874 2174.16945 534.32661
bias: mean(obs-pred.) -10.98624 -24.24786 -12.06537
Total number of coefficients 10.00000 4.00000 1.00000
Number of unique coefficients 10.00000 4.00000 1.00000
Number of unique climate coefficients 6.00000 3.00000 1.00000
Number of unique soils coefficients 4.00000 1.00000 0.00000

Visualizations of Model Predictions and Residuals – using best lambda model

observed vs. predicted values

If the 1se lambda has no terms (is an intercept only model), use the 1/2 se lambda in subsequent figures

if (length(prednames_fig_1se) == 0) {
  mod_secondBest <- fit_glm_halfse
  name_secondBestMod <- "1/2 SE Model"
  prednames_secondBestMod <- prednames_fig_halfse
} else {
  mod_secondBest <- fit_glm_se
  name_secondBestMod <- "1 SE Model"
  prednames_secondBestMod <- prednames_fig_1se
}

Predicting on the data

  # create prediction for each each model
# (i.e. for each fire proporation variable)
predict_by_response <- function(mod, df) {
  df_out <- df
  response_name <- paste0("biomass_MgPerHect", "_pred")
  preds <- predict(mod, newx= df_out, #s="lambda.min", 
                                     type = "response")
  preds <- preds -2
  preds[preds<0] <- 0
  #preds[preds>100] <- 100
  df_out <- df_out %>% cbind(preds)
   colnames(df_out)[ncol(df_out)] <- response_name
  return(df_out)
}

pred_glm1 <- predict_by_response(fit_glm_bestLambda, X[,2:ncol(X)])

## back-transform the 
# add back in true y values
pred_glm1 <- pred_glm1 %>% 
  cbind(modDat_1_s[,c("biomass_MgPerHect", "response_transformed")])

# add back in lat/long data 
pred_glm1 <- pred_glm1 %>% 
  cbind(modDat_1_s[,c("Long", "Lat")])

# calculate residuals
pred_glm1$resid <- pred_glm1[,"biomass_MgPerHect"] - pred_glm1[,paste0("biomass_MgPerHect", "_pred")]
pred_glm1$extremeResid <- NA
pred_glm1[pred_glm1$resid > 70 | pred_glm1$resid < -70,"extremeResid"] <- 1

# calculate residuals as percentages of the total 
pred_glm1$resid_perc <- (pred_glm1$resid / pred_glm1[,"biomass_MgPerHect"]) * 100

# plot(x = pred_glm1[,response],
#      y = pred_glm1[,paste0("biomass_MgPerHect", "_pred")],
#      xlab = "observed values", ylab = "predicted values")
# points(x = pred_glm1[!is.na(pred_glm1$extremeResid), response],
#        y = pred_glm1[!is.na(pred_glm1$extremeResid), paste0("biomass_MgPerHect", "_pred")],
#        col = "red")
pred_glm1_1se <- predict_by_response(mod_secondBest, X[,2:ncol(X)])

# add back in true y values
pred_glm1_1se <- pred_glm1_1se %>% 
  cbind(modDat_1_s[,c("biomass_MgPerHect", "response_transformed")])

# add back in lat/long data 
pred_glm1_1se <- pred_glm1_1se %>% 
  cbind(modDat_1_s[,c("Long", "Lat")])

# calculate residuals
pred_glm1_1se$resid <- pred_glm1_1se[,"biomass_MgPerHect"] - pred_glm1_1se[,paste0("biomass_MgPerHect", "_pred")]
pred_glm1_1se$extremeResid <- NA
pred_glm1_1se[pred_glm1_1se$resid > 70 | pred_glm1_1se$resid < -70,"extremeResid"] <- 1

# calculate residuals as percentages of the total 
pred_glm1_1se$resid_perc <- (pred_glm1_1se$resid / pred_glm1_1se[,"biomass_MgPerHect"]) * 100

Maps of Observations, Predictions, and Residuals=

Observations across the temporal range of the dataset

pred_glm1 <- pred_glm1 %>% 
  mutate(resid = .[["biomass_MgPerHect"]] - .[[paste0("biomass_MgPerHect","_pred")]]) 

# rasterize
# get reference raster
test_rast <-  rast("../../../Data_raw/dayMet/rawMonthlyData/orders/70e0da02b9d2d6e8faa8c97d211f3546/Daymet_Monthly_V4R1/data/daymet_v4_prcp_monttl_na_1980.tif") %>% 
  terra::aggregate(fact = 8, fun = "mean")
## |---------|---------|---------|---------|=========================================                                          
## add ecoregion boundaries (for our ecoregion level model)
regions <- sf::st_read(dsn = "../../../Data_raw/Level2Ecoregions/", layer = "NA_CEC_Eco_Level2") 
## Reading layer `NA_CEC_Eco_Level2' from data source 
##   `/Users/astears/Documents/Dropbox_static/Work/NAU_USGS_postdoc/PED_vegClimModels/Data_raw/Level2Ecoregions' 
##   using driver `ESRI Shapefile'
## Simple feature collection with 2261 features and 8 fields
## Geometry type: POLYGON
## Dimension:     XY
## Bounding box:  xmin: -4334052 ymin: -3313739 xmax: 3324076 ymax: 4267265
## Projected CRS: Sphere_ARC_INFO_Lambert_Azimuthal_Equal_Area
regions <- regions %>% 
  st_transform(crs = st_crs(test_rast)) %>% 
  st_make_valid() #%>% 
  #st_crop(st_bbox(test_rast))
# 
# goodRegions_temp <- st_overlaps(y = cropped_states, x = regions, sparse = FALSE) %>% 
#   rowSums() 
# goodRegions <- regions[goodRegions_temp != 0,]

ecoregionLU <- data.frame("NA_L1NAME" = sort(unique(regions$NA_L1NAME)), 
                        "newRegion" = c(NA, "Forest", "dryShrubGrass", 
                                        "dryShrubGrass", "Forest", "dryShrubGrass",
                                       "dryShrubGrass", "Forest", "Forest", 
                                       "dryShrubGrass", "Forest", "Forest", 
                                       "Forest", "Forest", "dryShrubGrass", 
                                       NA
                                        ))
goodRegions <- regions %>% 
  left_join(ecoregionLU)
mapRegions <- goodRegions %>% 
  filter(!is.na(newRegion)) %>% 
  group_by(newRegion) %>% 
  summarise(geometry = sf::st_union(geometry)) %>% 
  ungroup() %>% 
  st_simplify(dTolerance = 1000)
#mapview(mapRegions)
# rasterize data
plotObs <- pred_glm1 %>% 
         drop_na(paste("biomass_MgPerHect")) %>% 
  #slice_sample(n = 5e4) %>%
  terra::vect(geom = c("Long", "Lat")) %>% 
  terra::set.crs(crs(test_rast)) %>% 
  terra::rasterize(y = test_rast, 
                   field = "biomass_MgPerHect", 
                   fun = mean) #%>% 
  #terra::aggregate(fact = 2, fun = mean, na.rm = TRUE) %>% 
  #terra::crop(ext(-1950000, 1000000, -1800000, 1000000))

# get the extent of this particular raster, and crop it accordingly
tempExt <- crds(plotObs, na.rm = TRUE)

plotObs_2 <- plotObs %>% 
  crop(ext(min(tempExt[,1]), max(tempExt[,1]),
           min(tempExt[,2]), max(tempExt[,2])) 
       )
# make figures
map_obs <- ggplot() +
geom_spatraster(data = plotObs_2) + 
  geom_sf(data=cropped_states %>% st_transform(crs = st_crs(test_rast)) %>% st_crop(st_bbox(plotObs_2)),fill=NA ) +
  geom_sf(data = mapRegions, fill = NA, col = "orchid", lwd = .5) +
labs(title = paste0("Observations of ", "biomass_MgPerHect", " in the ",ecoregion, " ecoregion")) +
  scale_fill_gradient2(low = "brown",
                       mid = "wheat" ,
                       high = "darkgreen" , 
                       midpoint = 0,   na.value = "grey20") + 
  xlim(st_bbox(plotObs_2)[c(1,3)]) + 
  ylim(st_bbox(plotObs_2)[c(2,4)])

hist_obs <- ggplot(pred_glm1) + 
  geom_histogram(aes(.data[["biomass_MgPerHect"]]), fill = "lightgrey", col = "darkgrey")

library(ggpubr)
ggarrange(map_obs, hist_obs, heights = c(3,1), ncol = 1)

Predictions across the temporal range of the dataset

# rasterize data
plotPred <- pred_glm1 %>% 
         drop_na(paste0("biomass_MgPerHect","_pred")) %>% 
  #slice_sample(n = 5e4) %>%
  terra::vect(geom = c("Long", "Lat")) %>% 
  terra::set.crs(crs(test_rast)) %>% 
  terra::rasterize(y = test_rast, 
                   field = paste0("biomass_MgPerHect","_pred"), 
                   fun = mean) #%>% 
  #terra::aggregate(fact = 2, fun = mean, na.rm = TRUE) %>% 
  #terra::crop(ext(-1950000, 1000000, -1800000, 1000000))

# get the point location of those predictions that are > 600
highPred_points <- pred_glm1 %>% 
  filter(.[[paste0("biomass_MgPerHect","_pred")]] > 700 | 
           .[[paste0("biomass_MgPerHect", "_pred")]] < 0) %>% 
  terra::vect(geom = c("Long", "Lat")) %>% 
  terra::set.crs(crs(test_rast)) 

# get the extent of this particular raster, and crop it accordingly
tempExt <- crds(plotPred, na.rm = TRUE)

plotPred_2 <- plotPred %>% 
  crop(ext(min(tempExt[,1]), max(tempExt[,1]),
           min(tempExt[,2]), max(tempExt[,2])) 
       )
 # make figures
map_preds1 <- ggplot() +
geom_spatraster(data = plotPred_2) + 
  geom_sf(data=cropped_states %>% st_transform(crs = st_crs(test_rast)) %>% st_crop(st_bbox(plotObs_2)),fill=NA )  + 
  geom_sf(data = mapRegions, fill = NA, col = "orchid", lwd = .5) +
  geom_sf(data = highPred_points, col = "red") +
labs(title = paste0("Predictions from the 'best lambda' fitted model of ", "biomass_MgPerHect", " in the ",ecoregion, " ecoregion"),
     subtitle =  "bestLambda model\n 
     red points show predictions greater than 700 Mg/hect")  +
  scale_fill_gradient2(low = "wheat",
                       high = "darkgreen" , 
                       midpoint = 0,   
                       na.value = "grey20",
                       limits = c(0,max(terra::values(plotPred), na.rm = TRUE))) + 
  xlim(st_bbox(plotObs_2)[c(1,3)]) + 
  ylim(st_bbox(plotObs_2)[c(2,4)])

hist_preds1 <- ggplot(pred_glm1) + 
  geom_histogram(aes(.data[[paste0("biomass_MgPerHect", "_pred")]]), fill = "lightgrey", col = "darkgrey")#+ 
  #xlim(c(0,700))

ggarrange(map_preds1, hist_preds1, heights = c(3,1), ncol = 1)

# rasterize data
plotPred <- pred_glm1_1se %>% 
         drop_na(paste0("biomass_MgPerHect","_pred")) %>% 
  #slice_sample(n = 5e4) %>%
  terra::vect(geom = c("Long", "Lat")) %>% 
  terra::set.crs(crs(test_rast)) %>% 
  terra::rasterize(y = test_rast, 
                   field = paste0("biomass_MgPerHect","_pred"), 
                   fun = mean) #%>% 
  #terra::aggregate(fact = 2, fun = mean, na.rm = TRUE) %>% 
  #terra::crop(ext(-1950000, 1000000, -1800000, 1000000))

# get the point location of those predictions that are > 100
highPred_points <- pred_glm1_1se %>% 
  filter(.[[paste0("biomass_MgPerHect","_pred")]] > 700 | 
           .[[paste0("biomass_MgPerHect", "_pred")]] < 0) %>% 
  terra::vect(geom = c("Long", "Lat")) %>% 
  terra::set.crs(crs(test_rast)) 

# get the extent of this particular raster, and crop it accordingly
tempExt <- crds(plotPred, na.rm = TRUE)

plotPred_2 <- plotPred %>% 
  crop(ext(min(tempExt[,1]), max(tempExt[,1]),
           min(tempExt[,2]), max(tempExt[,2])) 
       )
# make figures
map_preds2 <- ggplot() +
geom_spatraster(data = plotPred_2) + 
  geom_sf(data=cropped_states %>% st_transform(crs = st_crs(test_rast)) %>% st_crop(st_bbox(plotObs_2)),fill=NA )  + 
  geom_sf(data = mapRegions, fill = NA, col = "orchid", lwd = .5) +
  geom_sf(data = highPred_points, col = "red") +
labs(title = paste0("Predictions from the '1SE lambda' fitted model of ", "biomass_MgPerHect", " in the ",ecoregion, " ecoregion"),
     subtitle =  name_secondBestMod)  +
  scale_fill_gradient2(low = "wheat",
                       high = "darkgreen" , 
                       #midpoint = 100,   
                       na.value = "grey20",
                       limits = c(0,max(terra::values(plotPred), na.rm = TRUE))) + 
  xlim(st_bbox(plotObs_2)[c(1,3)]) + 
  ylim(st_bbox(plotObs_2)[c(2,4)])

hist_preds2 <- ggplot(pred_glm1_1se) + 
  geom_histogram(aes(.data[[paste0("biomass_MgPerHect", "_pred")]]), fill = "lightgrey", col = "darkgrey")#+ 
  #xlim(c(0,200))

ggarrange(map_preds2, hist_preds2, heights = c(3,1), ncol = 1)

Residuals as a percentage of prediction ((resid - prediction)*100) for best SE lambda model

# rasterize data
plotResid_rast <- pred_glm1 %>% 
         drop_na(resid_perc) %>% 
  #slice_sample(n = 5e4) %>%
  terra::vect(geom = c("Long", "Lat")) %>% 
  terra::set.crs(crs(test_rast)) %>% 
  terra::rasterize(y = test_rast, 
                   field = "resid_perc", 
                   fun = mean) #%>% 
  #terra::aggregate(fact = 2, fun = mean, na.rm = TRUE) %>% 
  #terra::crop(ext(-1950000, 1000000, -1800000, 1000000))

# get the extent of this particular raster, and crop it accordingly
tempExt <- crds(plotResid_rast, na.rm = TRUE)

plotResid_rast_2 <- plotResid_rast %>% 
  crop(ext(min(tempExt[,1]), max(tempExt[,1]),
           min(tempExt[,2]), max(tempExt[,2])) 
       )

# identify locations where residuals are >100 or < -100
badResids_high <- pred_glm1 %>% 
  filter(resid > 100)  %>% 
  terra::vect(geom = c("Long", "Lat")) %>% 
  terra::set.crs(crs(test_rast)) 
badResids_low <- pred_glm1 %>% 
  filter(resid < -100)  %>% 
  terra::vect(geom = c("Long", "Lat")) %>% 
  terra::set.crs(crs(test_rast)) 
# make figures
map <- ggplot() +
geom_spatraster(data =plotResid_rast_2) + 
  geom_sf(data=cropped_states %>% st_transform(crs = st_crs(test_rast)) %>% st_crop(st_bbox(plotObs_2)),fill=NA )  + 
  geom_sf(data = mapRegions, fill = NA, col = "orchid", lwd = .5) +
  geom_sf(data = badResids_high, col = "blue") +
  geom_sf(data = badResids_low, col = "red") +
labs(title = paste0("Resids. as a percentage (obs. - pred.)/obs. * 100 from the ", ecoregion," ecoregion-wide model of ",  "biomass_MgPerHect"),
     subtitle = "bestLambda model \n red points indicate locations that have residuals below -200% \n blue points indicate locations that have residuals above 200%") +
  scale_fill_gradient2(low = "red",
                       mid = "white" ,
                       high = "blue" , 
                       midpoint = 0,   na.value = "grey20",
                       limits = c(-100 ,100)
                       ) + 
  xlim(st_bbox(plotObs_2)[c(1,3)]) + 
  ylim(st_bbox(plotObs_2)[c(2,4)])
hist <- ggplot(pred_glm1) + 
  geom_histogram(aes(resid), fill = "lightgrey", col = "darkgrey") + 
  geom_text(aes(x = min(resid)*.9, y = 1500, label = paste0("min = ", round(min(resid),2)))) +
  geom_text(aes(x = max(resid)*.9, y = 1500, label = paste0("max = ", round(max(resid),2)))) + 
  geom_vline(aes(xintercept = mean(resid)))

ggarrange(map, hist, heights = c(3,1), ncol = 1)

Residuals as a percentage of prediction ((resid - prediction)*100) for second best SE lambda model

# rasterize data
plotResid_rast <- pred_glm1_1se %>% 
         drop_na(resid_perc) %>% 
  #slice_sample(n = 5e4) %>%
  terra::vect(geom = c("Long", "Lat")) %>% 
  terra::set.crs(crs(test_rast)) %>% 
  terra::rasterize(y = test_rast, 
                   field = "resid_perc", 
                   fun = mean) #%>% 
  #terra::aggregate(fact = 2, fun = mean, na.rm = TRUE) %>% 
  #terra::crop(ext(-1950000, 1000000, -1800000, 1000000))

# get the extent of this particular raster, and crop it accordingly
tempExt <- crds(plotResid_rast, na.rm = TRUE)

plotResid_rast_2 <- plotResid_rast %>% 
  crop(ext(min(tempExt[,1]), max(tempExt[,1]),
           min(tempExt[,2]), max(tempExt[,2])) 
       )

# identify locations where residuals are >100 or < -100
badResids_high <- pred_glm1_1se %>% 
  filter(resid > 100)  %>% 
  terra::vect(geom = c("Long", "Lat")) %>% 
  terra::set.crs(crs(test_rast)) 
badResids_low <- pred_glm1_1se %>% 
  filter(resid < -100)  %>% 
  terra::vect(geom = c("Long", "Lat")) %>% 
  terra::set.crs(crs(test_rast)) 
# make figures
map <- ggplot() +
geom_spatraster(data =plotResid_rast_2) + 
  geom_sf(data=cropped_states %>% st_transform(crs = st_crs(test_rast)) %>% st_crop(st_bbox(plotObs_2)),fill=NA )  + 
  geom_sf(data = mapRegions, fill = NA, col = "orchid", lwd = .5) +
  geom_sf(data = badResids_high, col = "blue") +
  geom_sf(data = badResids_low, col = "red") +
labs(title = paste0("Resids. as a percentage (obs. - pred.)/obs. * 100 from the ", ecoregion," ecoregion-wide model of ", "biomass_MgPerHect"),
     subtitle = paste0(name_secondBestMod,"\n red points indicate locations that have residuals below -200% \n blue points indicate locations that have residuals above 200%")) +
  scale_fill_gradient2(low = "red",
                       mid = "white" ,
                       high = "blue" , 
                       midpoint = 0,   na.value = "grey20",
                       limits = c(-100,100)
                       ) + 
  xlim(st_bbox(plotObs_2)[c(1,3)]) + 
  ylim(st_bbox(plotObs_2)[c(2,4)])
hist <- ggplot(pred_glm1_1se) + 
  geom_histogram(aes(resid), fill = "lightgrey", col = "darkgrey") + 
  geom_text(aes(x = min(resid)*.9, y = 1500, label = paste0("min = ", round(min(resid),2)))) +
  geom_text(aes(x = max(resid)*.9, y = 1500, label = paste0("max = ", round(max(resid),2))))+ 
  geom_vline(aes(xintercept = mean(resid)))

ggarrange(map, hist, heights = c(3,1), ncol = 1)

Are there biases of the model predictions across year/lat/long?

# plot residuals against Year
# yearResidMod_bestLambda <- ggplot(pred_glm1) + 
#   geom_point(aes(x = jitter(Year), y = resid), alpha = .1) + 
#   geom_smooth(aes(x = Year, y = resid)) + 
#   xlab("Year") + 
#   ylab("Residuals") +
#   ggtitle("from best lamba model")
# yearResidMod_1seLambda <- ggplot(pred_glm1_1se) + 
#   geom_point(aes(x = jitter(Year), y = resid), alpha = .1) + 
#   geom_smooth(aes(x = Year, y = resid)) + 
#   xlab("Year") + 
#   ylab("Residuals") +
#   ggtitle(paste0("from ", name_secondBestMod))

# plot residuals against Lat
latResidMod_bestLambda <- ggplot(pred_glm1) + 
  geom_point(aes(x = Lat, y = resid), alpha = .1) + 
  geom_smooth(aes(x = Lat, y = resid)) + 
  xlab("Latitude") + 
  ylab("Residuals") +
  ggtitle("from best lamba model")
latResidMod_1seLambda <- ggplot(pred_glm1_1se) + 
  geom_point(aes(x = Lat, y = resid), alpha = .1) + 
  geom_smooth(aes(x = Lat, y = resid)) + 
  xlab("Latitude") + 
  ylab("Residuals") +
  ggtitle(paste0("from ", name_secondBestMod))

# plot residuals against Long
longResidMod_bestLambda <- ggplot(pred_glm1) + 
  geom_point(aes(x = Long, y = resid), alpha = .1) + 
  geom_smooth(aes(x = Long, y = resid)) + 
  xlab("Longitude") + 
  ylab("Residuals") +
  ggtitle("from best lamba model")
longResidMod_1seLambda <- ggplot(pred_glm1_1se) + 
  geom_point(aes(x = Long, y = resid), alpha = .1) + 
  geom_smooth(aes(x = Long, y = resid)) + 
  xlab("Longitude") + 
  ylab("Residuals") +
  ggtitle(paste0("from ", name_secondBestMod))

library(patchwork)
#(yearResidMod_bestLambda + yearResidMod_1seLambda) / 
(  latResidMod_bestLambda + latResidMod_1seLambda) /
(  longResidMod_bestLambda + longResidMod_1seLambda)

Quantile plots

Binning predictor variables into “Deciles” (actually percentiles) and looking at the mean predicted probability for each percentile. The use of the word Decentiles is just a legacy thing (they started out being actual Percentiles)

# get deciles for best lambda model 
if (length(prednames_fig) == 0) {
  print("The best lambda model only contains one predictor (an intercept), so decile plots aren't possible to generate")
} else {
  pred_glm1_deciles <- predvars2deciles(pred_glm1,
                                      response_vars = response_vars,
                                        pred_vars = prednames_fig, 
                                       cut_points = seq(0, 1, 0.005))
}
# get deciles for 1 SE lambda model 
if (length(prednames_secondBestMod) == 0) {
  print("The 1SE (or 1/2 SE) lambda model only contains one predictor (an intercept), so decile plots aren't possible to generate")
} else {
  pred_glm1_deciles_1se <- predvars2deciles(pred_glm1_1se,
                                      response_vars = response_vars,
                                        pred_vars = prednames_secondBestMod, 
                                       cut_points = seq(0, 1, 0.005))
}

Here is a quick version of LOESS curves fit to raw data (to double-check the quantile plot calculations)

# 
# if (length(prednames_fig) == 0) {
#   print("The model only contains one predictor (an intercept), so decile plots aren't possible to generate")
# } else {
#   pred_glm1 %>%
#   dplyr::select(all_of(c(prednames_fig, response_vars))) %>%
#   pivot_longer(cols = prednames_fig)  %>%
#   ggplot() +
#   facet_wrap(~name, scales = "free") +
#   geom_point(aes(x = value, y =  .data[[paste(response)]]), col = "darkblue", alpha = .1)  + # observed values
#   geom_point(aes(x = value, y = .data[[response_vars[2]]]), col = "lightblue", alpha = .1) + # model-predicted values
#   geom_smooth(aes(x = value, y =  .data[[paste(response)]]), col = "black", se = FALSE) +
#   geom_smooth(aes(x = value, y = .data[[response_vars[2]]]), col = "brown", se = FALSE) +
#   ggtitle(label = "dark blue points = observations;
#           light blue points = predictions;
#           black line = observations;
#           brown line = predictions") + 
#     ggplot2::ylim(c(0,1000))
# 
# }

Below are the actual quantile plots (note that the predictor variables are scaled)

if (length(prednames_fig) == 0) {
  print("The model only contains one predictor (an intercept), so decile plots aren't possible to generate")
} else {

# publication quality version
g3 <- decile_dotplot_pq(df = pred_glm1_deciles, response = "biomass_MgPerHect", IQR = TRUE,
                        CI = FALSE
                        ) + ggtitle("Decile Plot")

g4 <- add_dotplot_inset(g3, df = pred_glm1_deciles, response = "biomass_MgPerHect", dfRaw = pred_glm1, add_smooth = TRUE, deciles = FALSE)

  
if(save_figs) {
  png(paste0("figures/quantile_plots/quantile_plot_", response,  "_",ecoregion,".png"), 
     units = "in", res = 600, width = 5.5, height = 3.5 )
    print(g4)
  dev.off()
}

g4
}

if (length(prednames_secondBestMod) == 0) {
  print("The 1 se lambda model only contains one predictor (an intercept), so decile plots aren't possible to generate")

  } else {

# publication quality version
g3 <- decile_dotplot_pq(pred_glm1_deciles_1se, response =  "biomass_MgPerHect", IQR = TRUE) + ggtitle("Decile Plot")

g4 <- add_dotplot_inset(g3, df = pred_glm1_deciles_1se, response =  "biomass_MgPerHect", dfRaw = pred_glm1_1se, add_smooth = TRUE, deciles = FALSE)

  
if(save_figs) {
  png(paste0("figures/quantile_plots/quantile_plot_", response,  "_",ecoregion,".png"), 
     units = "in", res = 600, width = 5.5, height = 3.5 )
    print(g4)
  dev.off()
}

g4
}

Deciles Filtered

20th and 80th percentiles for each climate variable

df <- pred_glm1[, prednames_fig] #%>% 
  #mutate(MAT = MAT - 273.15) # k to c
quantiles <- purrr::map(df, quantile, probs = c(0.2, 0.8), na.rm = TRUE)

Filtered ‘Decile’ plots of data. These plots show each vegetation variable, but only based on data that falls into the upper and lower two deciles of each predictor variable.

if (length(prednames_fig) == 0) {
  print("The model only contains one predictor (an intercept), so decile plots aren't possible to generate")
} else {
pred_glm1_deciles_filt <- predvars2deciles( pred_glm1, 
                         response_vars = response_vars,
                         pred_vars = prednames_fig,
                         filter_var = TRUE,
                         filter_vars = prednames_fig,
                         cut_points = seq(0, 1, 0.005)) 

decile_dotplot_filtered_pq(pred_glm1_deciles_filt, xvars = prednames_fig, response = "biomass_MgPerHect"
                           )
#decile_dotplot_filtered_pq(pred_glm1_deciles_filt)

}

Filtered quantile figure with middle 2 deciles also shown

if (length(prednames_fig) == 0) {
  print("The model only contains one predictor (an intercept), so decile plots aren't possible to generate")
} else {
pred_glm1_deciles_filt_mid <- predvars2deciles(pred_glm1, 
                         response_vars = response_vars,
                         pred_vars = prednames_fig,
                         filter_vars = prednames_fig,
                         filter_var = TRUE,
                         add_mid = TRUE,
                         cut_points = seq(0, 1, 0.005))

g <- decile_dotplot_filtered_pq(df = pred_glm1_deciles_filt_mid, response = "biomass_MgPerHect", 
                                xvars = prednames_fig)
g

if(save_figs) {
jpeg(paste0("figures/quantile_plots/quantile_plot_filtered_mid_v1", , ".jpeg"),
     units = "in", res = 600, width = 5.5, height = 6 )
  g 
dev.off()
}
}

Show model RMSE w/in each quantile

# get deciles for best lambda model 
if (length(prednames_fig) == 0) {
  print("The best lambda model only contains one predictor (an intercept), so decile plots aren't possible to generate")
} else {
  pred_glm1_deciles %>% 
    ggplot(aes(x = mean_value, y = RMSE)) +
    facet_wrap(~name, scales = "free_x")+
    geom_point(alpha = .2, size = .5) + 
    geom_smooth(lwd = .5) + 
    xlab("Scaled predictor value") + 
    ggtitle("RMSE by decile for bestLambda model")
}

# get deciles for 1 SE lambda model 
if (length(prednames_secondBestMod) == 0) {
  print("The 1SE (or 1/2 SE) lambda model only contains one predictor (an intercept), so decile plots aren't possible to generate")
} else {
  pred_glm1_deciles_1se %>% 
    ggplot(aes(x = mean_value, y = RMSE)) +
    facet_wrap(~name, scales = "free_x")+
    geom_point(alpha = .2, size = .5) + 
    geom_smooth(lwd = .5) + 
    xlab("Scaled predictor value") + 
    ggtitle(paste0("RMSE by decile for ", name_secondBestMod, "model"))
}

Cross-validation

Using best lambda model

Use terms from global model to re-fit and predict on different held out regions

Figures show residuals for each of the models fit to held-out ecoregions

These models were fit to six ecoregions, and then predict on the indicated heldout ecoregion

if (length(prednames_fig) == 0) {
  print("The model only contains one predictor (an intercept), so cross validation isn't practical")
} else {
  
## code from Tredennick et al. 2020
# try each separate level II ecoregion as a test set
# make a list to hold output data
outList <- vector(mode = "list", length = length(sort(unique(modDat_1_s$NA_L2NAME))))
# obs_pred <- data.frame(ecoregion = character(),obs = numeric(),
#                        pred_opt = numeric(), pred_null = numeric()#,
#                        #pred_nopenalty = numeric()
#                        )

## get the model specification from the global model
mat <- as.matrix(coef(fit_glm_bestLambda, s = "lambda.min"))
mat2 <- mat[mat[,1] != 0,]

f_cv <- as.formula(paste0("response_transformed ~ ", paste0(names(mat2)[2:length(names(mat2))], collapse = " + ")))

X_cv <- model.matrix(object = f_cv, data = modDat_1_s)
# get response variable
y_cv <- as.matrix(modDat_1_s[,"response_transformed"])

  
# now, loop through so with each iteration, a different ecoregion is held out
 for(i_eco in sort(unique(modDat_1_s$NA_L2NAME))){

  # split into training and test sets
  test_eco <- i_eco
  print(test_eco)
  # identify the rowID of observations to be in the training and test datasets
  train <- which(modDat_1_s$NA_L2NAME!=test_eco) # data for all ecoregions that aren't 'i_eco'
  test <- which(modDat_1_s$NA_L2NAME==test_eco) # data for the ecoregion that is 'i_eco'

  trainDat_all <- modDat_1_s %>% 
    slice(train) %>% 
    dplyr::select(-newRegion)
  testDat_all <- modDat_1_s %>% 
    slice(test) %>% 
    dplyr::select(-newRegion)

  # get the model matrices for input and response variables for cross validation model specification
  X_train <- as.matrix(X_cv[train,])
  X_test <- as.matrix(X_cv[test,])

  y_train <- modDat_1_s[train,"response_transformed"]
  y_test <- modDat_1_s[test,"response_transformed"]
  
  # get the model matrices for input and response variables for original model specification
  X_train_glob <- as.matrix(X[train,])
  X_test_glob <- as.matrix(X[test,])

  y_train_glob <- modDat_1_s[train,"response_transformed"]
  y_test_glob <- modDat_1_s[test,"response_transformed"]

  train_eco <- modDat_1_s$NA_L2NAME[train]

  ## just try a regular glm w/ the components from the global model
  fit_i <- glm(data = trainDat_all, formula = f_cv, 
    ,
               family =  stats::Gamma(link = "log")
    )
    
  # lasso model predictions with the optimal lambda (back transformed)
  optimal_pred <- predict(fit_i, newdata= testDat_all, type = "response") 
  # null model and predictions
  # the "null" model in this case is the global model 
  # predict on the test data for this iteration w/ the global model (back transformed)
  null_pred <- predict.glm(fit_glm_bestLambda, newdata = testDat_all, type = "response") 

  
  # save data
  tmp <- data.frame(ecoRegion_holdout = rep(test_eco,length(y_test)),
                    obs=y_test - 2,
                    pred_opt=optimal_pred- 2, 
                    pred_null=null_pred- 2#,
                    #pred_nopenalty=nopen_pred
                    ) %>%
    cbind(testDat_all)
  
  # calculate RMSE, bias, etc. of 
  # RMSE of CV model 
  RMSE_optimal <- yardstick::rmse(data = data.frame(optimal_pred,"y_test" = (y_test)), truth = "y_test", estimate = "optimal_pred")[1,]$.estimate
  # RMSE of global model
  RMSE_null <- yardstick::rmse(data = data.frame(null_pred,"y_test" = (y_test)), truth = "y_test", estimate = "null_pred")[1,]$.estimate
  # bias of CV model
  bias_optimal <- mean((y_test) - optimal_pred)
  # bias of global model
  bias_null <-  mean((y_test) - null_pred )
  
  # put output into a list
  tmpList <- list("testRegion" = i_eco,
    "modelObject" = fit_i,
       "modelPredictions" = tmp, 
    "performanceMetrics" = data.frame("RMSE_cvModel" = RMSE_optimal, 
                                      "RMSE_globalModel" = RMSE_null, 
                                      "bias_cvModel" = bias_optimal, 
                                      "bias_globalModel" = bias_null))

  # save model outputs
  outList[[which(sort(unique(modDat_1_s$NA_L2NAME)) == i_eco)]] <- tmpList
 }
}
## [1] "ATLANTIC HIGHLANDS"
## [1] "CENTRAL USA PLAINS"
## [1] "COLD DESERTS"
## [1] "MEDITERRANEAN CALIFORNIA AND UPPER GILA MOUNTAINS"
## [1] "MIXED WOOD SHIELD"
## [1] "SOUTH CENTRAL SEMIARID PRAIRIES"
## [1] "SOUTHEASTERN AND MIXED WOOD PLAINS"
## [1] "TAMAULIPAS-TEXAS SEMIARID PLAIN"
## [1] "TEMPERATE PRAIRIES"
## [1] "WARM DESERTS"
## [1] "WEST-CENTRAL SEMIARID PRAIRIES"
## [1] "WESTERN CORDILLERA AND WEST COAST FOREST"
## [1] "WESTERN SIERRA MADRE PIEDMONT"

Below are the RMSE and bias values for predictions made for each holdout level II ecoregion, compared to predictions from the global model for that same ecoregion

# table of model performance
purrr::map(outList, .f = function(x) {
  cbind(data.frame("holdout region" = x$testRegion),  x$performanceMetrics)
}
) %>% 
  purrr::list_rbind() %>% 
  kable(col.names = c("Held-out ecoregion", "RMSE of CV model", "RMSE of global model", 
                      "bias of CV model - mean(obs-pred.)", "bias of global model- mean(obs-pred.)"), 
        caption = "Performance of Cross Validation using 'best lambda' model specification") %>%
kable_styling(bootstrap_options = c("striped", "hover", "condensed")) 
Performance of Cross Validation using ‘best lambda’ model specification
Held-out ecoregion RMSE of CV model RMSE of global model bias of CV model - mean(obs-pred.) bias of global model- mean(obs-pred.)
ATLANTIC HIGHLANDS 199.055642 116.096369 -141.0532025 -75.4105124
CENTRAL USA PLAINS 24.479179 22.887240 -17.1469490 -15.2692511
COLD DESERTS 19.757791 16.292757 -8.9857676 -4.0079758
MEDITERRANEAN CALIFORNIA AND UPPER GILA MOUNTAINS 32.181800 31.710894 10.1634520 9.0275201
MIXED WOOD SHIELD 55.674559 45.870487 49.4097546 37.1222235
SOUTH CENTRAL SEMIARID PRAIRIES 10.396242 9.794247 -1.9927527 -1.2519227
SOUTHEASTERN AND MIXED WOOD PLAINS 44.735220 38.527539 19.2622796 -1.9297816
TAMAULIPAS-TEXAS SEMIARID PLAIN 9.027339 8.854776 5.2077342 4.8950920
TEMPERATE PRAIRIES 9.525129 9.311502 -2.7347976 -1.5752696
WARM DESERTS 4.353684 4.361076 -0.7715408 -1.1416552
WEST-CENTRAL SEMIARID PRAIRIES 9.267518 8.382007 -5.2255009 -3.8167005
WESTERN CORDILLERA AND WEST COAST FOREST 9400.276962 625.629089 -410.0083718 -79.8817663
WESTERN SIERRA MADRE PIEDMONT 6.886548 6.885400 -0.0805669 -0.0914379
# visualize model predictions
for (i in 1:length(sort(unique(modDat_1_s$NA_L2NAME)))) {
  holdoutRegion <- outList[[i]]$testRegion
  predictionData <- outList[[i]]$modelPredictions
  modTerms <- as.matrix(coef(outList[[i]]$modelObject)) %>%
    as.data.frame() %>%
    filter(V1!=0) %>%
    rownames()

  # calculate residuals
  predictionData <- predictionData %>%
  mutate(resid = .[["obs"]] - .[["pred_opt"]] ,
         resid_globMod = .[["obs"]]  - .[["pred_null"]]) %>% 
    mutate(resid_perc = (resid/.[["obs"]] )*100)


# rasterize
# use 'test_rast' from earlier

  # rasterize data
plotObs <- predictionData %>%
         drop_na(paste("biomass_MgPerHect")) %>%
  #slice_sample(n = 5e4) %>%
  terra::vect(geom = c("Long", "Lat")) %>%
  terra::set.crs(crs(test_rast)) %>%
  terra::rasterize(y = test_rast,
                   field = "resid_perc",
                   fun = mean) #%>%
  #terra::aggregate(fact = 2, fun = mean, na.rm = TRUE) %>%
  #terra::crop(ext(-1950000, 1000000, -1800000, 1000000))

tempExt <- crds(plotObs, na.rm = TRUE)

plotObs_2 <- plotObs %>% 
  crop(ext(min(tempExt[,1]), max(tempExt[,1]),
           min(tempExt[,2]), max(tempExt[,2])) 
       )

# identify locations where residuals are >100 or < -100
badResids_high <- predictionData %>%
  filter(resid_perc > 500)  %>%
  terra::vect(geom = c("Long", "Lat")) %>%
  terra::set.crs(crs(test_rast))
badResids_low <- predictionData %>%
  filter(resid_perc < -500)  %>%
  terra::vect(geom = c("Long", "Lat")) %>%
  terra::set.crs(crs(test_rast))


# make figures
# make histogram
hist_i <- ggplot(predictionData) +
  geom_histogram(aes(resid_globMod), col = "darkgrey", fill = "lightgrey") +
  xlab(c("Residuals as % (obs. - pred.)/pred. * 100"))
# make map
map_i <-  ggplot() +
geom_spatraster(data = plotObs_2) +
  geom_sf(data=cropped_states %>% st_transform(crs = st_crs(test_rast)) %>% st_crop(st_bbox(plotObs_2)),fill=NA ) +
  geom_sf(data = mapRegions, fill = NA, col = "orchid", lwd = .5) +
  geom_sf(data = badResids_high, col = "blue") +
  geom_sf(data = badResids_low, col = "red") +
labs(title = paste0("Residuals as % ((obs. - pred.)/pred.)*100 for predictions of \n", holdoutRegion, " \n from a model fit to other ecoregions"),
     subtitle = paste0(response, " ~ ", paste0( modTerms, collapse = " + "))) +
  scale_fill_gradient2(low = "red",
                       mid = "white" ,
                       high = "blue" ,
                       midpoint = 0,   na.value = "grey20",
                       limits = c(-500, 500)
                       )  + 
  xlim(st_bbox(plotObs_2)[c(1,3)]) + 
  ylim(st_bbox(plotObs_2)[c(2,4)])

 assign(paste0("residPlot_",holdoutRegion),
   value = ggarrange(map_i, hist_i, heights = c(3,1), ncol = 1)
)

}

  lapply(unique(modDat_1_s$NA_L2NAME), FUN = function(x) {
    get(paste0("residPlot_", x))
  })
## [[1]]

## 
## [[2]]

## 
## [[3]]

## 
## [[4]]

## 
## [[5]]

## 
## [[6]]

## 
## [[7]]

## 
## [[8]]

## 
## [[9]]

## 
## [[10]]

## 
## [[11]]

## 
## [[12]]

## 
## [[13]]

Using second best lambda model (either 1se or 1/2se)

Use terms from global model to re-fit and predict on different held out regions

Figures show residuals for each of the models fit to held-out ecoregions

These models were fit to six ecoregions, and then predict on the indicated heldout ecoregion

if (length(prednames_secondBestMod) == 0) {
  print("The model only contains one predictor (an intercept), so cross validation isn't practical")
} else {

## code from Tredennick et al. 2020
# try each separate level II ecoregion as a test set
# make a list to hold output data
outList <- vector(mode = "list", length = length(sort(unique(modDat_1_s$NA_L2NAME))))
# obs_pred <- data.frame(ecoregion = character(),obs = numeric(),
#                        pred_opt = numeric(), pred_null = numeric()#,
#                        #pred_nopenalty = numeric()
#                        )

## get the model specification from the global model
mat <- as.matrix(coef(mod_secondBest, s = "lambda.min"))
mat2 <- mat[mat[,1] != 0,]

f_cv <- as.formula(paste0("response_transformed ~ ", paste0(names(mat2)[2:length(names(mat2))], collapse = " + ")))

X_cv <- model.matrix(object = f_cv, data = modDat_1_s)
# get response variable
y_cv <- as.matrix(modDat_1_s[,"biomass_MgPerHect"])

  
# now, loop through so with each iteration, a different ecoregion is held out
 for(i_eco in sort(unique(modDat_1_s$NA_L2NAME))){

  # split into training and test sets
  test_eco <- i_eco
  print(test_eco)
  # identify the rowID of observations to be in the training and test datasets
  train <- which(modDat_1_s$NA_L2NAME!=test_eco) # data for all ecoregions that aren't 'i_eco'
  test <- which(modDat_1_s$NA_L2NAME==test_eco) # data for the ecoregion that is 'i_eco'

  trainDat_all <- modDat_1_s %>% 
    slice(train) %>% 
    dplyr::select(-newRegion)
  testDat_all <- modDat_1_s %>% 
    slice(test) %>% 
    dplyr::select(-newRegion)

  # get the model matrices for input and response variables for cross validation model specification
  X_train <- as.matrix(X_cv[train,])
  X_test <- as.matrix(X_cv[test,])

  y_train <- modDat_1_s[train,"response_transformed"]
  y_test <- modDat_1_s[test,"response_transformed"]
  
  # get the model matrices for input and response variables for original model specification
  X_train_glob <- as.matrix(X[train,])
  X_test_glob <- as.matrix(X[test,])

  y_train_glob <- modDat_1_s[train,"response_transformed"]
  y_test_glob <- modDat_1_s[test,"response_transformed"]

  train_eco <- modDat_1_s$NA_L2NAME[train]

  ## just try a regular glm w/ the components from the global model
  fit_i <- glm(data = trainDat_all, formula = f_cv, 
               family =  stats::Gamma(link = "log")
    )

    coef(fit_i)
    
  # lasso model predictions with the optimal lambda
  optimal_pred <- predict(fit_i, newdata= testDat_all, type = "response")  
  # null model and predictions
  # the "null" model in this case is the global model
  # predict on the test data for this iteration w/ the global model 
  null_pred <- predict.glm(mod_secondBest, newdata = testDat_all, type = "response") 

  # save data
  tmp <- data.frame(ecoRegion_holdout = rep(test_eco,length(y_test)),
                    obs=y_test - 2,
                    pred_opt=optimal_pred -2, 
                    pred_null=null_pred-2#,
                    #pred_nopenalty=nopen_pred
                    ) %>%
    cbind(testDat_all)
    
  # calculate RMSE, bias, etc. of 
  # RMSE of CV model 
  RMSE_optimal <- yardstick::rmse(data = data.frame(optimal_pred, "y_test" = (y_test)), truth = "y_test", estimate = "optimal_pred")[1,]$.estimate
  # RMSE of global model
  RMSE_null <- yardstick::rmse(data = data.frame(null_pred,  "y_test" = (y_test)), truth = "y_test", estimate = "null_pred")[1,]$.estimate
  # bias of CV model
  bias_optimal <- mean((y_test) - optimal_pred)
  # bias of global model
  bias_null <-  mean((y_test) - null_pred )
  
  # put output into a list
  tmpList <- list("testRegion" = i_eco,
    "modelObject" = fit_i,
       "modelPredictions" = tmp, 
    "performanceMetrics" = data.frame("RMSE_cvModel" = RMSE_optimal, 
                                      "RMSE_globalModel" = RMSE_null, 
                                      "bias_cvModel" = bias_optimal, 
                                      "bias_globalModel" = bias_null))

  # save model outputs
  outList[[which(sort(unique(modDat_1_s$NA_L2NAME)) == i_eco)]] <- tmpList
 }
}
## [1] "ATLANTIC HIGHLANDS"
## [1] "CENTRAL USA PLAINS"
## [1] "COLD DESERTS"
## [1] "MEDITERRANEAN CALIFORNIA AND UPPER GILA MOUNTAINS"
## [1] "MIXED WOOD SHIELD"
## [1] "SOUTH CENTRAL SEMIARID PRAIRIES"
## [1] "SOUTHEASTERN AND MIXED WOOD PLAINS"
## [1] "TAMAULIPAS-TEXAS SEMIARID PLAIN"
## [1] "TEMPERATE PRAIRIES"
## [1] "WARM DESERTS"
## [1] "WEST-CENTRAL SEMIARID PRAIRIES"
## [1] "WESTERN CORDILLERA AND WEST COAST FOREST"
## [1] "WESTERN SIERRA MADRE PIEDMONT"

Below are the RMSE and bias values for predictions made for each holdout level II ecoregion, compared to predictions from the global model for that same ecoregion

if (length(prednames_secondBestMod) == 0) {
  print("The model only contains one predictor (an intercept), so cross validation isn't practical")
} else {
# table of model performance
purrr::map(outList, .f = function(x) {
  cbind(data.frame("holdout region" = x$testRegion),  x$performanceMetrics)
}
) %>% 
  purrr::list_rbind() %>% 
  kable(col.names = c("Held-out ecoregion", "RMSE of CV model", "RMSE of global model", 
                      "bias of CV model - mean(obs-pred.)", "bias of global model - mean(obs-pred.)"), 
        caption = "Performance of Cross Validation using '1 SE lambda' model specification") %>%
kable_styling(bootstrap_options = c("striped", "hover", "condensed")) 
}
Performance of Cross Validation using ‘1 SE lambda’ model specification
Held-out ecoregion RMSE of CV model RMSE of global model bias of CV model - mean(obs-pred.) bias of global model - mean(obs-pred.)
ATLANTIC HIGHLANDS 65.698871 63.714891 54.864947 51.957969
CENTRAL USA PLAINS 31.971581 31.071209 -27.079464 -26.061591
COLD DESERTS 14.678683 14.657744 1.404775 1.219285
MEDITERRANEAN CALIFORNIA AND UPPER GILA MOUNTAINS 33.066476 32.888663 11.912363 11.470605
MIXED WOOD SHIELD 59.881536 58.618321 51.665249 50.243026
SOUTH CENTRAL SEMIARID PRAIRIES 26.595857 25.002613 -17.571955 -15.129581
SOUTHEASTERN AND MIXED WOOD PLAINS 70.160184 47.636383 -37.113889 -12.711882
TAMAULIPAS-TEXAS SEMIARID PLAIN 8.676764 8.643448 -5.111486 -5.055653
TEMPERATE PRAIRIES 26.060952 24.397740 -23.328948 -21.653072
WARM DESERTS 8.085537 7.156922 -6.753141 -5.618665
WEST-CENTRAL SEMIARID PRAIRIES 13.453399 12.223104 -10.682591 -9.107178
WESTERN CORDILLERA AND WEST COAST FOREST 3827.495427 1625.504787 -100.673490 -52.344669
WESTERN SIERRA MADRE PIEDMONT 8.100583 8.071354 -4.486782 -4.433864
if (length(prednames_secondBestMod) == 0) {
  print("The model only contains one predictor (an intercept), so cross validation isn't practical")
} else {
for (i in 1:length(unique(modDat_1_s$NA_L2NAME))) {
  holdoutRegion <- outList[[i]]$testRegion
  predictionData <- outList[[i]]$modelPredictions
  modTerms <- as.matrix(coef(outList[[i]]$modelObject)) %>%
    as.data.frame() %>%
    filter(V1!=0) %>%
    rownames()

  # calcuye residuals
  predictionData <- predictionData %>%
  mutate(resid = .[["obs"]] - .[["pred_opt"]] ,
         resid_globMod = .[["obs"]]  - .[["pred_null"]]) %>% 
    mutate(resid_perc = (resid/.[["obs"]] )*100)


# rasterize
# use 'test_rast' from earlier

  # rasterize data
plotObs <- predictionData %>%
         drop_na(paste("biomass_MgPerHect")) %>%
  #slice_sample(n = 5e4) %>%
  terra::vect(geom = c("Long", "Lat")) %>%
  terra::set.crs(crs(test_rast)) %>%
  terra::rasterize(y = test_rast,
                   field = "resid_perc",
                   fun = mean) #%>%
  #terra::aggregate(fact = 2, fun = mean, na.rm = TRUE) %>%
  #terra::crop(ext(-1950000, 1000000, -1800000, 1000000))

tempExt <- crds(plotObs, na.rm = TRUE)

plotObs_2 <- plotObs %>% 
  crop(ext(min(tempExt[,1]), max(tempExt[,1]),
           min(tempExt[,2]), max(tempExt[,2])) 
       )

# identify locations where residuals are >100 or < -100
badResids_high <- predictionData %>% 
  filter(resid_perc > 500)  %>% 
  terra::vect(geom = c("Long", "Lat")) %>% 
  terra::set.crs(crs(test_rast)) 
badResids_low <- predictionData %>% 
  filter(resid_perc < -500)  %>% 
  terra::vect(geom = c("Long", "Lat")) %>% 
  terra::set.crs(crs(test_rast)) 


# make figures
# make histogram
hist_i <- ggplot(predictionData) +
  geom_histogram(aes(resid_globMod), col = "darkgrey", fill = "lightgrey") +
  xlab(c("Residuals (obs. - pred.)"))
# make map
map_i <-  ggplot() +
geom_spatraster(data = plotObs_2) +
  geom_sf(data=cropped_states %>% st_transform(crs = st_crs(test_rast)) %>% st_crop(st_bbox(plotObs_2)),fill=NA ) +
  geom_sf(data = mapRegions, fill = NA, col = "orchid", lwd = .5) +
  geom_sf(data = badResids_high, col = "blue") +
  geom_sf(data = badResids_low, col = "red") +
labs(title = paste0("Residuals as % ((obs. - pred.)/pred.)*100 for predictions of \n", holdoutRegion, " \n from a model fit to other ecoregions"),
     subtitle = paste0("biomass_MgPerHect", " ~ ", paste0( modTerms, collapse = " + "))) +
  scale_fill_gradient2(low = "red",
                       mid = "white" ,
                       high = "blue" ,
                       midpoint = 0,   na.value = "grey20",
                       limits = c(-500, 500))  + 
  xlim(st_bbox(plotObs_2)[c(1,3)]) + 
  ylim(st_bbox(plotObs_2)[c(2,4)])

 assign(paste0("residPlot_",holdoutRegion),
   value = ggarrange(map_i, hist_i, heights = c(3,1), ncol = 1)
)

}

  lapply(unique(modDat_1_s$NA_L2NAME), FUN = function(x) {
    get(paste0("residPlot_", x))
  })
}
## [[1]]

## 
## [[2]]

## 
## [[3]]

## 
## [[4]]

## 
## [[5]]

## 
## [[6]]

## 
## [[7]]

## 
## [[8]]

## 
## [[9]]

## 
## [[10]]

## 
## [[11]]

## 
## [[12]]

## 
## [[13]]

Save output

## save the coefficients for the models (best lambda, 1/2se lambda, 1se lambda)
if(trimAnom == TRUE) {
saveRDS(coefs, file = paste0("./models/modelCoefficients_trimAnom_", ecoregion, "_", "biomass_MgPerHect",".rds")) 
saveRDS(uniqueCoeffs, file = paste0("./models/modelMetrics_trimAnom_", ecoregion, "_", "biomass_MgPerHect",".rds")) 
} else {
saveRDS(coefs, file = paste0("./models/modelCoefficients_", ecoregion, "_", "biomass_MgPerHect",".rds")) 
saveRDS(uniqueCoeffs, file = paste0("./models/modelMetrics_", ecoregion, "_", "biomass_MgPerHect",".rds")) 
}
# make a table
## partial dependence plots
#vip::vip(mod_glmFinal, num_features = 15)

#pdp_all_vars(mod_glmFinal, mod_vars = pred_vars, ylab = 'probability',train = df_small)

#caret::varImp(fit)

session info

Hash of current commit (i.e. to ID the version of the code used)

system("git rev-parse HEAD", intern=TRUE)
## [1] "7678f7daa542d0e9cfbb5cac65c7ba07b976c342"

Packages etc.

sessionInfo()
## R version 4.4.0 (2024-04-24)
## Platform: aarch64-apple-darwin20
## Running under: macOS 15.6
## 
## Matrix products: default
## BLAS:   /Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/lib/libRblas.0.dylib 
## LAPACK: /Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/lib/libRlapack.dylib;  LAPACK version 3.12.0
## 
## locale:
## [1] en_US.UTF-8/en_US.UTF-8/en_US.UTF-8/C/en_US.UTF-8/en_US.UTF-8
## 
## time zone: America/Denver
## tzcode source: internal
## 
## attached base packages:
## [1] stats     graphics  grDevices utils     datasets  methods   base     
## 
## other attached packages:
##  [1] ggpubr_0.6.0               factoextra_1.0.7          
##  [3] USA.state.boundaries_1.0.1 glmnet_4.1-8              
##  [5] Matrix_1.7-0               kableExtra_1.4.0          
##  [7] rsample_1.2.1              here_1.0.1                
##  [9] StepBeta_2.1.0             ggtext_0.1.2              
## [11] knitr_1.49                 gridExtra_2.3             
## [13] pdp_0.8.2                  GGally_2.2.1              
## [15] lubridate_1.9.4            forcats_1.0.0             
## [17] stringr_1.5.1              dplyr_1.1.4               
## [19] purrr_1.0.4                readr_2.1.5               
## [21] tidyr_1.3.1                tibble_3.2.1              
## [23] tidyverse_2.0.0            caret_6.0-94              
## [25] lattice_0.22-6             ggplot2_3.5.1             
## [27] sf_1.0-20                  tidyterra_0.6.1           
## [29] terra_1.8-21               ggspatial_1.1.9           
## [31] dtplyr_1.3.1               patchwork_1.3.0           
## 
## loaded via a namespace (and not attached):
##   [1] RColorBrewer_1.1-3   rstudioapi_0.17.1    jsonlite_1.9.1      
##   [4] shape_1.4.6.1        magrittr_2.0.3       modeltools_0.2-23   
##   [7] farver_2.1.2         rmarkdown_2.29       vctrs_0.6.5         
##  [10] rstatix_0.7.2        htmltools_0.5.8.1    broom_1.0.7         
##  [13] Formula_1.2-5        pROC_1.18.5          sass_0.4.9          
##  [16] parallelly_1.37.1    KernSmooth_2.23-22   bslib_0.9.0         
##  [19] plyr_1.8.9           sandwich_3.1-0       zoo_1.8-12          
##  [22] cachem_1.1.0         commonmark_1.9.1     lifecycle_1.0.4     
##  [25] iterators_1.0.14     pkgconfig_2.0.3      R6_2.6.1            
##  [28] fastmap_1.2.0        future_1.33.2        digest_0.6.37       
##  [31] colorspace_2.1-1     furrr_0.3.1          rprojroot_2.0.4     
##  [34] labeling_0.4.3       yardstick_1.3.1      timechange_0.3.0    
##  [37] mgcv_1.9-1           abind_1.4-8          compiler_4.4.0      
##  [40] proxy_0.4-27         aod_1.3.3            withr_3.0.2         
##  [43] backports_1.5.0      carData_3.0-5        betareg_3.1-4       
##  [46] DBI_1.2.3            ggstats_0.9.0        ggsignif_0.6.4      
##  [49] MASS_7.3-60.2        lava_1.8.0           classInt_0.4-10     
##  [52] gtools_3.9.5         ModelMetrics_1.2.2.2 tools_4.4.0         
##  [55] units_0.8-5          lmtest_0.9-40        future.apply_1.11.2 
##  [58] nnet_7.3-19          glue_1.8.0           nlme_3.1-164        
##  [61] gridtext_0.1.5       grid_4.4.0           reshape2_1.4.4      
##  [64] generics_0.1.3       recipes_1.1.0        gtable_0.3.6        
##  [67] tzdb_0.4.0           class_7.3-22         data.table_1.17.0   
##  [70] hms_1.1.3            car_3.1-2            xml2_1.3.7          
##  [73] flexmix_2.3-19       markdown_1.13        ggrepel_0.9.5       
##  [76] foreach_1.5.2        pillar_1.10.1        splines_4.4.0       
##  [79] survival_3.5-8       tidyselect_1.2.1     svglite_2.1.3       
##  [82] stats4_4.4.0         xfun_0.51            hardhat_1.4.0       
##  [85] timeDate_4032.109    stringi_1.8.4        yaml_2.3.10         
##  [88] evaluate_1.0.3       codetools_0.2-20     cli_3.6.4           
##  [91] rpart_4.1.23         systemfonts_1.2.1    munsell_0.5.1       
##  [94] jquerylib_0.1.4      Rcpp_1.0.14          globals_0.16.3      
##  [97] parallel_4.4.0       gower_1.0.1          listenv_0.9.1       
## [100] viridisLite_0.4.2    ipred_0.9-15         scales_1.3.0        
## [103] prodlim_2024.06.25   e1071_1.7-14         combinat_0.0-8      
## [106] rlang_1.1.5          cowplot_1.1.3